mailitics

Category: cs.LG

  • A note on the impossibility of conditional PAC-efficient reasoning in large language models

    A note on the impossibility of conditional PAC-efficient reasoning in large language models arXiv:2512.03057v1 Announce Type: new Abstract: We prove an impossibility result for conditional Probably Approximately Correct (PAC)-efficient reasoning in large language models. While recent work has established marginal PAC efficiency guarantees for composite models that switch between expensive expert models and cheaper fast…

  • Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback

    Uncertainty Quantification for Large Language Model Reward Learning under Heterogeneous Human Feedback arXiv:2512.03208v1 Announce Type: new Abstract: We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of model-generated answers and their…

  • Novelty detection on path space

    Novelty detection on path space arXiv:2512.03243v1 Announce Type: new Abstract: We frame novelty detection on path space as a hypothesis testing problem with signature-based test statistics. Using transportation-cost inequalities of Gasteratos and Jacquier (2023), we obtain tail bounds for false positive rates that extend beyond Gaussian measures to laws of RDE solutions with smooth bounded…

  • Iterative Tilting for Diffusion Fine-Tuning

    Iterative Tilting for Diffusion Fine-Tuning arXiv:2512.03234v1 Announce Type: new Abstract: We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $exp(lambda r)$ into $N$ sequential smaller tilts, each admitting a tractable score update via first-order Taylor expansion. This requires only forward evaluations of the…

  • Colored Markov Random Fields for Probabilistic Topological Modeling

    Colored Markov Random Fields for Probabilistic Topological Modeling arXiv:2512.03727v1 Announce Type: new Abstract: Probabilistic Graphical Models (PGMs) encode conditional dependencies among random variables using a graph -nodes for variables, links for dependencies- and factorize the joint distribution into lower-dimensional components. This makes PGMs well-suited for analyzing complex systems and supporting decision-making. Recent advances in topological…

  • Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing

    Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing arXiv:2512.02495v1 Announce Type: new Abstract: Inverse problems arise across scientific and engineering domains, where the goal is to infer hidden parameters or physical fields from indirect and noisy observations. Classical approaches, such as variational regularization and Bayesian inference, provide well established theoretical…

  • Laplace Approximation For Tensor Train Kernel Machines In System Identification

    Laplace Approximation For Tensor Train Kernel Machines In System Identification arXiv:2512.02532v1 Announce Type: new Abstract: To address the scalability limitations of Gaussian process (GP) regression, several approximation techniques have been proposed. One such method is based on tensor networks, which utilizes an exponential number of basis functions without incurring exponential computational cost. However, extending this…

  • Revisiting Theory of Contrastive Learning for Domain Generalization

    Revisiting Theory of Contrastive Learning for Domain Generalization arXiv:2512.02831v1 Announce Type: new Abstract: Contrastive learning is among the most popular and powerful approaches for self-supervised representation learning, where the goal is to map semantically similar samples close together while separating dissimilar ones in the latent space. Existing theoretical methods assume that downstream task classes are…

  • Spatiotemporal Pyramid Flow Matching for Climate Emulation

    Spatiotemporal Pyramid Flow Matching for Climate Emulation arXiv:2512.02268v1 Announce Type: cross Abstract: Generative models have the potential to transform the way we emulate Earth’s changing climate. Previous generative approaches rely on weather-scale autoregression for climate emulation, but this is inherently slow for long climate horizons and has yet to demonstrate stable rollouts under nonstationary forcings.…

  • DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants

    DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants arXiv:2512.00252v1 Announce Type: new Abstract: Data assimilation (DA) is a cornerstone of scientific and engineering applications, combining model forecasts with sparse and noisy observations to estimate latent system states. Classical DA methods, such as the ensemble Kalman filter, rely on Gaussian approximations and heuristic tuning (e.g.,…

  • An RKHS Perspective on Tree Ensembles

    An RKHS Perspective on Tree Ensembles arXiv:2512.00397v1 Announce Type: new Abstract: Random Forests and Gradient Boosting are among the most effective algorithms for supervised learning on tabular data. Both belong to the class of tree-based ensemble methods, where predictions are obtained by aggregating many randomized regression trees. In this paper, we develop a theoretical framework…

  • No-Regret Gaussian Process Optimization of Time-Varying Functions

    No-Regret Gaussian Process Optimization of Time-Varying Functions arXiv:2512.00517v1 Announce Type: new Abstract: Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings. However, for time-varying objectives, it is known that no-regret is unattainable under pure bandit feedback unless strong and…

  • Statistical-computational gap in multiple Gaussian graph alignment

    Statistical-computational gap in multiple Gaussian graph alignment arXiv:2512.00610v1 Announce Type: new Abstract: We investigate the existence of a statistical-computational gap in multiple Gaussian graph alignment. We first generalize a previously established informational threshold from Vassaux and Massouli’e (2025) to regimes where the number of observed graphs $p$ may also grow with the number of nodes…

  • Self-sufficient Independent Component Analysis via KL Minimizing Flows

    Self-sufficient Independent Component Analysis via KL Minimizing Flows arXiv:2512.00665v1 Announce Type: new Abstract: We study the problem of learning disentangled signals from data using non-linear Independent Component Analysis (ICA). Motivated by advances in self-supervised learning, we propose to learn self-sufficient signals: A recovered signal should be able to reconstruct a missing value of its own…

  • Algorithms and Scientific Software for Quasi-Monte Carlo, Fast Gaussian Process Regression, and Scientific Machine Learning

    Algorithms and Scientific Software for Quasi-Monte Carlo, Fast Gaussian Process Regression, and Scientific Machine Learning arXiv:2511.21915v1 Announce Type: new Abstract: Most scientific domains elicit the development of efficient algorithms and accessible scientific software. This thesis unifies our developments in three broad domains: Quasi-Monte Carlo (QMC) methods for efficient high-dimensional integration, Gaussian process (GP) regression for…

  • Sparse Multiple Kernel Learning: Alternating Best Response and Semidefinite Relaxations

    Sparse Multiple Kernel Learning: Alternating Best Response and Semidefinite Relaxations arXiv:2511.21890v1 Announce Type: new Abstract: We study Sparse Multiple Kernel Learning (SMKL), which is the problem of selecting a sparse convex combination of prespecified kernels for support vector binary classification. Unlike prevailing l1 regularized approaches that approximate a sparsifying penalty, we formulate the problem by…

  • A Sensitivity Approach to Causal Inference Under Limited Overlap

    A Sensitivity Approach to Causal Inference Under Limited Overlap arXiv:2511.22003v1 Announce Type: new Abstract: Limited overlap between treated and control groups is a key challenge in observational analysis. Standard approaches like trimming importance weights can reduce variance but introduce a fundamental bias. We propose a sensitivity framework for contextualizing findings under limited overlap, where we…

  • On the Effect of Regularization on Nonparametric Mean-Variance Regression

    On the Effect of Regularization on Nonparametric Mean-Variance Regression arXiv:2511.22004v1 Announce Type: new Abstract: Uncertainty quantification is vital for decision-making and risk assessment in machine learning. Mean-variance regression models, which predict both a mean and residual noise for each data point, provide a simple approach to uncertainty quantification. However, overparameterized mean-variance models struggle with signal-to-noise…

  • Support Vector Machine Classifier with Rescaled Huberized Pinball Loss

    Support Vector Machine Classifier with Rescaled Huberized Pinball Loss arXiv:2511.22065v1 Announce Type: new Abstract: Support vector machines are widely used in machine learning classification tasks, but traditional SVM models suffer from sensitivity to outliers and instability in resampling, which limits their performance in practical applications. To address these issues, this paper proposes a novel rescaled…

  • When Features Beat Noise: A Feature Selection Technique Through Noise-Based Hypothesis Testing

    When Features Beat Noise: A Feature Selection Technique Through Noise-Based Hypothesis Testing arXiv:2511.20851v1 Announce Type: new Abstract: Feature selection has remained a daunting challenge in machine learning and artificial intelligence, where increasingly complex, high-dimensional datasets demand principled strategies for isolating the most informative predictors. Despite widespread adoption, many established techniques suffer from notable limitations; some…

  • Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets

    Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets arXiv:2511.20888v1 Announce Type: new Abstract: This paper argues that DNNs implement a computational Occam’s razor — finding the `simplest’ algorithm that fits the data — and that this could explain their incredible and wide-ranging success over more traditional statistical methods. We start…

  • Geometric Calibration and Neutral Zones for Uncertainty-Aware Multi-Class Classification

    Geometric Calibration and Neutral Zones for Uncertainty-Aware Multi-Class Classification arXiv:2511.20960v1 Announce Type: new Abstract: Modern artificial intelligence systems make critical decisions yet often fail silently when uncertain. We develop a geometric framework for post-hoc calibration of neural network probability outputs, treating probability vectors as points on the $(c-1)$-dimensional probability simplex equipped with the Fisher–Rao metric.…

  • Nonconvex Penalized LAD Estimation in Partial Linear Models with DNNs: Asymptotic Analysis and Proximal Algorithms

    Nonconvex Penalized LAD Estimation in Partial Linear Models with DNNs: Asymptotic Analysis and Proximal Algorithms arXiv:2511.21115v1 Announce Type: new Abstract: This paper investigates the partial linear model by Least Absolute Deviation (LAD) regression. We parameterize the nonparametric term using Deep Neural Networks (DNNs) and formulate a penalized LAD problem for estimation. Specifically, our model exhibits…

  • Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference

    Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference arXiv:2511.21223v1 Announce Type: new Abstract: Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models that would otherwise be intractable. However, its formulation depends on expectations and divergences defined through high-dimensional integrals, often rendering analytical treatment impossible and necessitating heavy reliance on…

  • FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection

    FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection arXiv:2511.19476v1 Announce Type: new Abstract: Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free, which rely on…

  • Optimization and Regularization Under Arbitrary Objectives

    Optimization and Regularization Under Arbitrary Objectives arXiv:2511.19628v1 Announce Type: new Abstract: This study investigates the limitations of applying Markov Chain Monte Carlo (MCMC) methods to arbitrary objective functions, focusing on a two-block MCMC framework which alternates between Metropolis-Hastings and Gibbs sampling. While such approaches are often considered advantageous for enabling data-driven regularization, we show that…

  • Clustering Approaches for Mixed-Type Data: A Comparative Study

    Clustering Approaches for Mixed-Type Data: A Comparative Study arXiv:2511.19755v1 Announce Type: new Abstract: Clustering is widely used in unsupervised learning to find homogeneous groups of observations within a dataset. However, clustering mixed-type data remains a challenge, as few existing approaches are suited for this task. This study presents the state-of-the-art of these approaches and compares…

  • A Fully Probabilistic Tensor Network for Regularized Volterra System Identification

    A Fully Probabilistic Tensor Network for Regularized Volterra System Identification arXiv:2511.20457v1 Announce Type: new Abstract: Modeling nonlinear systems with Volterra series is challenging because the number of kernel coefficients grows exponentially with the model order. This work introduces Bayesian Tensor Network Volterra kernel machines (BTN-V), extending the Bayesian Tensor Network framework to Volterra system identification.…

  • Generative Modeling with Manifold Percolation

    Generative Modeling with Manifold Percolation arXiv:2511.20503v1 Announce Type: new Abstract: Generative modeling is typically framed as learning mapping rules, but from an observer’s perspective without access to these rules, the task manifests as disentangling the geometric support from the probability distribution. We propose that Continuum Percolation is uniquely suited for this support analysis, as the…

  • Quantum Fourier Transform Based Kernel for Solar Irrandiance Forecasting

    Quantum Fourier Transform Based Kernel for Solar Irrandiance Forecasting arXiv:2511.17698v1 Announce Type: new Abstract: This study proposes a Quantum Fourier Transform (QFT)-enhanced quantum kernel for short-term time-series forecasting. Each signal is windowed, amplitude-encoded, transformed by a QFT, then passed through a protective rotation layer to avoid the QFT/QFT adjoint cancellation; the resulting kernel is used…

  • Prequential posteriors

    Prequential posteriors arXiv:2511.17721v1 Announce Type: new Abstract: Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather prediction to online reinforcement learning. Deep generative forecasting models (DGFMs) have shown excellent performance in these areas, but assimilating data into such models is challenging due to their intractable…

  • Variational Estimators for Node Popularity Models

    Variational Estimators for Node Popularity Models arXiv:2511.17783v1 Announce Type: new Abstract: Node popularity is recognized as a key factor in modeling real-world networks, capturing heterogeneity in connectivity across communities. This concept is equally important in bipartite networks, where nodes in different partitions may exhibit varying popularity patterns, motivating models such as the Two-Way Node Popularity…

  • An operator splitting analysis of Wasserstein–Fisher–Rao gradient flows

    An operator splitting analysis of Wasserstein–Fisher–Rao gradient flows arXiv:2511.18060v1 Announce Type: new Abstract: Wasserstein-Fisher-Rao (WFR) gradient flows have been recently proposed as a powerful sampling tool that combines the advantages of pure Wasserstein (W) and pure Fisher-Rao (FR) gradient flows. Existing algorithmic developments implicitly make use of operator splitting techniques to numerically approximate the WFR…

  • Conformal Prediction for Compositional Data

    Conformal Prediction for Compositional Data arXiv:2511.18141v1 Announce Type: new Abstract: In this work, we propose a set of conformal prediction procedures tailored to compositional responses, where outcomes are proportions that must be positive and sum to one. Building on Dirichlet regression, we introduce a split conformal approach based on quantile residuals and a highest-density region…

  • BITS for GAPS: Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates

    BITS for GAPS: Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates arXiv:2511.16815v1 Announce Type: new Abstract: We introduce the Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS) framework to emulate latent components in hybrid physical systems. BITS for GAPS supports serial hybrid modeling, where known physics governs part of the system and…

  • Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition

    Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition arXiv:2511.16796v1 Announce Type: cross Abstract: Penalty-based methods have become popular for solving bilevel optimization (BLO) problems, thanks to their effective first-order nature. However, they often require inner-loop iterations to solve the lower-level (LL) problem and small outer-loop step sizes to handle the increased smoothness…

  • Gradient flow for deep equilibrium single-index models

    Gradient flow for deep equilibrium single-index models arXiv:2511.16976v1 Announce Type: cross Abstract: Deep equilibrium models (DEQs) have recently emerged as a powerful paradigm for training infinitely deep weight-tied neural networks that achieve state of the art performance across many modern machine learning tasks. Despite their practical success, theoretically understanding the gradient descent dynamics for training…

  • Atlas Gaussian processes on restricted domains and point clouds

    Atlas Gaussian processes on restricted domains and point clouds arXiv:2511.15822v1 Announce Type: new Abstract: In real-world applications, data often reside in restricted domains with unknown boundaries, or as high-dimensional point clouds lying on a lower-dimensional, nontrivial, unknown manifold. Traditional Gaussian Processes (GPs) struggle to capture the underlying geometry in such settings. Some existing methods assume…

  • Angular Graph Fractional Fourier Transform: Theory and Application

    Angular Graph Fractional Fourier Transform: Theory and Application arXiv:2511.16111v1 Announce Type: new Abstract: Graph spectral representations are fundamental in graph signal processing, offering a rigorous framework for analyzing and processing graph-structured data. The graph fractional Fourier transform (GFRFT) extends the classical graph Fourier transform (GFT) with a fractional-order parameter, enabling flexible spectral analysis while preserving…

  • Time dependent loss reweighting for flow matching and diffusion models is theoretically justified

    Time dependent loss reweighting for flow matching and diffusion models is theoretically justified arXiv:2511.16599v1 Announce Type: new Abstract: This brief note clarifies that, in Generator Matching (which subsumes a large family of flow matching and diffusion models over continuous, manifold, and discrete spaces), both the Bregman divergence loss and the linear parameterization of the generator…

  • Spectral Identifiability for Interpretable Probe Geometry

    Spectral Identifiability for Interpretable Probe Geometry arXiv:2511.16288v1 Announce Type: new Abstract: Linear probes are widely used to interpret and evaluate neural representations, yet their reliability remains unclear, as probes may appear accurate in some regimes but collapse unpredictably in others. We uncover a spectral mechanism behind this phenomenon and formalize it as the Spectral Identifiability…

  • Rate-optimal community detection near the KS threshold via node-robust algorithms

    Rate-optimal community detection near the KS threshold via node-robust algorithms arXiv:2511.16613v1 Announce Type: new Abstract: We study community detection in the emph{symmetric $k$-stochastic block model}, where $n$ nodes are evenly partitioned into $k$ clusters with intra- and inter-cluster connection probabilities $p$ and $q$, respectively. Our main result is a polynomial-time algorithm that achieves the minimax-optimal…

  • Convex Clustering Redefined: Robust Learning with the Median of Means Estimator

    Convex Clustering Redefined: Robust Learning with the Median of Means Estimator arXiv:2511.14784v1 Announce Type: new Abstract: Clustering approaches that utilize convex loss functions have recently attracted growing interest in the formation of compact data clusters. Although classical methods like k-means and its wide family of variants are still widely used, all of them require the…

  • Implicit Bias of the JKO Scheme

    Implicit Bias of the JKO Scheme arXiv:2511.14827v1 Announce Type: new Abstract: Wasserstein gradient flow provides a general framework for minimizing an energy functional $J$ over the space of probability measures on a Riemannian manifold $(M,g)$. Its canonical time-discretization, the Jordan-Kinderlehrer-Otto (JKO) scheme, produces for any step size $eta>0$ a sequence of probability distributions $rho_k^eta$ that…

  • Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit

    Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit arXiv:2511.15120v1 Announce Type: new Abstract: In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussian Multi-index model $f(boldsymbol{x})=g(boldsymbol{U}boldsymbol{x})$ with hidden subspace $boldsymbol{U}in mathbb{R}^{rtimes d}$, which is the…

  • Latent space analysis and generalization to out-of-distribution data

    Latent space analysis and generalization to out-of-distribution data arXiv:2511.15010v1 Announce Type: new Abstract: Understanding the relationships between data points in the latent decision space derived by the deep learning system is critical to evaluating and interpreting the performance of the system on real world data. Detecting textit{out-of-distribution} (OOD) data for deep learning systems continues to…

  • Beyond Uncertainty Sets: Leveraging Optimal Transport to Extend Conformal Predictive Distribution to Multivariate Settings

    Beyond Uncertainty Sets: Leveraging Optimal Transport to Extend Conformal Predictive Distribution to Multivariate Settings arXiv:2511.15146v1 Announce Type: new Abstract: Conformal prediction (CP) constructs uncertainty sets for model outputs with finite-sample coverage guarantees. A candidate output is included in the prediction set if its non-conformity score is not considered extreme relative to the scores observed on…

  • Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands

    Uncertainty-Calibrated Prediction of Randomly-Timed Biomarker Trajectories with Conformal Bands arXiv:2511.13911v1 Announce Type: new Abstract: Despite recent progress in predicting biomarker trajectories from real clinical data, uncertainty in the predictions poses high-stakes risks (e.g., misdiagnosis) that limit their clinical deployment. To enable safe and reliable use of such predictions in healthcare, we introduce a conformal method…

  • Knowledge vs. Experience: Asymptotic Limits of Impatience in Edge Tenants

    Knowledge vs. Experience: Asymptotic Limits of Impatience in Edge Tenants arXiv:2511.13763v1 Announce Type: new Abstract: We study how two information feeds, a closed-form Markov estimator of residual sojourn and an online trained actor-critic, affect reneging and jockeying in a dual M/M/1 system. Analytically, for unequal service rates and total-time patience, we show that total wait…

  • Empirical Likelihood for Random Forests and Ensembles

    Empirical Likelihood for Random Forests and Ensembles arXiv:2511.13934v1 Announce Type: new Abstract: We develop an empirical likelihood (EL) framework for random forests and related ensemble methods, providing a likelihood-based approach to quantify their statistical uncertainty. Exploiting the incomplete $U$-statistic structure inherent in ensemble predictions, we construct an EL statistic that is asymptotically chi-squared when subsampling…

  • Splat Regression Models

    Splat Regression Models arXiv:2511.14042v1 Announce Type: new Abstract: We introduce a highly expressive class of function approximators called Splat Regression Models. Model outputs are mixtures of heterogeneous and anisotropic bump functions, termed splats, each weighted by an output vector. The power of splat modeling lies in its ability to locally adjust the scale and direction…

  • SCOPE: Spectral Concentration by Distributionally Robust Joint Covariance-Precision Estimation

    SCOPE: Spectral Concentration by Distributionally Robust Joint Covariance-Precision Estimation arXiv:2511.14146v1 Announce Type: new Abstract: We propose a distributionally robust formulation for simultaneously estimating the covariance matrix and the precision matrix of a random vector.The proposed model minimizes the worst-case weighted sum of the Frobenius loss of the covariance estimator and Stein’s loss of the precision…

  • Generalized Inequality-based Approach for Probabilistic WCET Estimation

    Generalized Inequality-based Approach for Probabilistic WCET Estimation arXiv:2511.11682v1 Announce Type: new Abstract: Estimating the probabilistic Worst-Case Execution Time (pWCET) is essential for ensuring the timing correctness of real-time applications, such as in robot IoT systems and autonomous driving systems. While methods based on Extreme Value Theory (EVT) can provide tight bounds, they suffer from model…

  • FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition

    FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition arXiv:2511.11817v1 Announce Type: new Abstract: Time series forecasting is essential in a wide range of real world applications. Recently, frequency-domain methods have attracted increasing interest for their ability to capture global dependencies. However, when applied to non-stationary time series, these methods encounter the $textit{spectral…

  • PCA recovery thresholds in low-rank matrix inference with sparse noise

    PCA recovery thresholds in low-rank matrix inference with sparse noise arXiv:2511.11927v1 Announce Type: new Abstract: We study the high-dimensional inference of a rank-one signal corrupted by sparse noise. The noise is modelled as the adjacency matrix of a weighted undirected graph with finite average connectivity in the large size limit. Using the replica method from…

  • Bayesian–AI Fusion for Epidemiological Decision Making: Calibrated Risk, Honest Uncertainty, and Hyperparameter Intelligence

    Bayesian–AI Fusion for Epidemiological Decision Making: Calibrated Risk, Honest Uncertainty, and Hyperparameter Intelligence arXiv:2511.11983v1 Announce Type: new Abstract: Modern epidemiological analytics increasingly use machine learning models that offer strong prediction but often lack calibrated uncertainty. Bayesian methods provide principled uncertainty quantification, yet are viewed as difficult to integrate with contemporary AI workflows. This paper proposes…

  • PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning

    PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning arXiv:2511.12278v1 Announce Type: new Abstract: High-dimensional data often contain low-dimensional signals obscured by structured background noise, which limits the effectiveness of standard PCA. Motivated by contrastive learning, we address the problem of recovering shared signal subspaces from positive pairs, paired observations sharing the same…

  • Neural Local Wasserstein Regression

    Neural Local Wasserstein Regression arXiv:2511.10824v1 Announce Type: new Abstract: We study the estimation problem of distribution-on-distribution regression, where both predictors and responses are probability measures. Existing approaches typically rely on a global optimal transport map or tangent-space linearization, which can be restrictive in approximation capacity and distort geometry in multivariate underlying domains. In this paper,…

  • Heterogeneous Multisource Transfer Learning via Model Averaging for Positive-Unlabeled Data

    Heterogeneous Multisource Transfer Learning via Model Averaging for Positive-Unlabeled Data arXiv:2511.10919v1 Announce Type: new Abstract: Positive-Unlabeled (PU) learning presents unique challenges due to the lack of explicitly labeled negative samples, particularly in high-stakes domains such as fraud detection and medical diagnosis. To address data scarcity and privacy constraints, we propose a novel transfer learning with…

  • Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths

    Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths arXiv:2511.11161v1 Announce Type: new Abstract: This paper addresses the nonparametric estimation of the drift function over a compact domain for a time-homogeneous diffusion process, based on high-frequency discrete observations from $N$ independent trajectories. We propose a neural network-based estimator and derive…

  • Decomposing Direct and Indirect Biases in Linear Models under Demographic Parity Constraint

    Decomposing Direct and Indirect Biases in Linear Models under Demographic Parity Constraint arXiv:2511.11294v1 Announce Type: new Abstract: Linear models are widely used in high-stakes decision-making due to their simplicity and interpretability. Yet when fairness constraints such as demographic parity are introduced, their effects on model coefficients, and thus on how predictive bias is distributed across…

  • Bayesian Evaluation of Large Language Model Behavior

    Bayesian Evaluation of Large Language Model Behavior arXiv:2511.10661v1 Announce Type: cross Abstract: It is increasingly important to evaluate how text generation systems based on large language models (LLMs) behave, such as their tendency to produce harmful output or their sensitivity to adversarial inputs. Such evaluations often rely on a curated benchmark set of input prompts…

  • Siegel Neural Networks

    Siegel Neural Networks arXiv:2511.09577v1 Announce Type: new Abstract: Riemannian symmetric spaces (RSS) such as hyperbolic spaces and symmetric positive definite (SPD) manifolds have become popular spaces for representation learning. In this paper, we propose a novel approach for building discriminative neural networks on Siegel spaces, a family of RSS that is largely unexplored in machine…

  • Generalized infinite dimensional Alpha-Procrustes based geometries

    Generalized infinite dimensional Alpha-Procrustes based geometries arXiv:2511.09801v1 Announce Type: new Abstract: This work extends the recently introduced Alpha-Procrustes family of Riemannian metrics for symmetric positive definite (SPD) matrices by incorporating generalized versions of the Bures-Wasserstein (GBW), Log-Euclidean, and Wasserstein distances. While the Alpha-Procrustes framework has unified many classical metrics in both finite- and infinite- dimensional…

  • Masked Mineral Modeling: Continent-Scale Mineral Prospecting via Geospatial Infilling

    Masked Mineral Modeling: Continent-Scale Mineral Prospecting via Geospatial Infilling arXiv:2511.09722v1 Announce Type: new Abstract: Minerals play a critical role in the advanced energy technologies necessary for decarbonization, but characterizing mineral deposits hidden underground remains costly and challenging. Inspired by recent progress in generative modeling, we develop a learning method which infers the locations of minerals…

  • Theory and computation for structured variational inference

    Theory and computation for structured variational inference arXiv:2511.09897v1 Announce Type: new Abstract: Structured variational inference constitutes a core methodology in modern statistical applications. Unlike mean-field variational inference, the approximate posterior is assumed to have interdependent structure. We consider the natural setting of star-structured variational inference, where a root variable impacts all the other ones. We…

  • Operator Models for Continuous-Time Offline Reinforcement Learning

    Operator Models for Continuous-Time Offline Reinforcement Learning arXiv:2511.10383v1 Announce Type: new Abstract: Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control, direct interaction with the environment is often unsafe or impractical, motivating offline reinforcement learning from historical data. However, there is limited statistical understanding of the approximation errors…

  • Optimal Control of the Future via Prospective Foraging

    Optimal Control of the Future via Prospective Foraging arXiv:2511.08717v1 Announce Type: new Abstract: Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in either reinforcement learning or online learning. While powerful, these frameworks for learning are mathematically distinct from Probably Approximately Correct (PAC) learning, which…

  • The Probably Approximately Correct Learning Model in Computational Learning Theory

    The Probably Approximately Correct Learning Model in Computational Learning Theory arXiv:2511.08791v1 Announce Type: new Abstract: This survey paper gives an overview of various known results on learning classes of Boolean functions in Valiant’s Probably Approximately Correct (PAC) learning model and its commonly studied variants. Rocco A. Servedio Go to original source

  • Effects of label noise on the classification of outlier observations

    Effects of label noise on the classification of outlier observations arXiv:2511.08808v1 Announce Type: new Abstract: This study investigates the impact of adding noise to the training set classes in classification tasks using the BCOPS algorithm (Balanced and Conformal Optimized Prediction Sets), proposed by Guan & Tibshirani (2022). The BCOPS algorithm is an application of conformal…

  • Robust Sampling for Active Statistical Inference

    Robust Sampling for Active Statistical Inference arXiv:2511.08991v1 Announce Type: new Abstract: Active statistical inference is a new method for inference with AI-assisted data collection. Given a budget on the number of labeled data points that can be collected and assuming access to an AI predictive model, the basic idea is to improve estimation accuracy by…

  • Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation

    Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation arXiv:2511.09002v1 Announce Type: new Abstract: Self-consuming generative models have received significant attention over the last few years. In this paper, we study a self-consuming generative model with heterogeneous preferences that is a generalization of the model in Ferbach et al. (2024). The model…

  • Tractable Instances of Bilinear Maximization: Implementing LinUCB on Ellipsoids

    Tractable Instances of Bilinear Maximization: Implementing LinUCB on Ellipsoids arXiv:2511.07504v1 Announce Type: new Abstract: We consider the maximization of $x^top theta$ over $(x,theta) in mathcal{X} times Theta$, with $mathcal{X} subset mathbb{R}^d$ convex and $Theta subset mathbb{R}^d$ an ellipsoid. This problem is fundamental in linear bandits, as the learner must solve it at every time step…

  • Robust Experimental Design via Generalised Bayesian Inference

    Robust Experimental Design via Generalised Bayesian Inference arXiv:2511.07671v1 Announce Type: new Abstract: Bayesian optimal experimental design is a principled framework for conducting experiments that leverages Bayesian inference to quantify how much information one can expect to gain from selecting a certain design. However, accurate Bayesian inference relies on the assumption that one’s statistical model of…

  • Infinite-Dimensional Operator/Block Kaczmarz Algorithms: Regret Bounds and $lambda$-Effectiveness

    Infinite-Dimensional Operator/Block Kaczmarz Algorithms: Regret Bounds and $lambda$-Effectiveness arXiv:2511.07604v1 Announce Type: new Abstract: We present a variety of projection-based linear regression algorithms with a focus on modern machine-learning models and their algorithmic performance. We study the role of the relaxation parameter in generalized Kaczmarz algorithms and establish a priori regret bounds with explicit $lambda$-dependence to…

  • Distributionally Robust Online Markov Game with Linear Function Approximation

    Distributionally Robust Online Markov Game with Linear Function Approximation arXiv:2511.07831v1 Announce Type: new Abstract: The sim-to-real gap, where agents trained in a simulator face significant performance degradation during testing, is a fundamental challenge in reinforcement learning. Extansive works adopt the framework of distributionally robust RL, to learn a policy that acts robustly under worst case…

  • PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure

    PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure arXiv:2511.07997v1 Announce Type: new Abstract: We revisit the problem of generating synthetic data under differential privacy. To address the core limitations of marginal-based methods, we propose the Private Adaptive Generative Adversarial Network with Bayes Network Structure (PrAda-GAN), which integrates the strengths of both GAN-based…

  • Benchmarking of Clustering Validity Measures Revisited

    Benchmarking of Clustering Validity Measures Revisited arXiv:2511.05983v1 Announce Type: new Abstract: Validation plays a crucial role in the clustering process. Many different internal validity indexes exist for the purpose of determining the best clustering solution(s) from a given collection of candidates, e.g., as produced by different algorithms or different algorithm hyper-parameters. In this study, we…

  • Sparsity via Hyperpriors: A Theoretical and Algorithmic Study under Empirical Bayes Framework

    Sparsity via Hyperpriors: A Theoretical and Algorithmic Study under Empirical Bayes Framework arXiv:2511.06235v1 Announce Type: new Abstract: This paper presents a comprehensive analysis of hyperparameter estimation within the empirical Bayes framework (EBF) for sparse learning. By studying the influence of hyperpriors on the solution of EBF, we establish a theoretical connection between the choice of…

  • Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces

    Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces arXiv:2511.06239v1 Announce Type: new Abstract: Learning-based methods for sampling from the Gibbs distribution in finite-dimensional spaces have progressed quickly, yet theory and algorithmic design for infinite-dimensional function spaces remain limited. This gap persists despite their strong potential for sampling the paths of conditional diffusion processes, enabling…

  • Fast Riemannian-manifold Hamiltonian Monte Carlo for hierarchical Gaussian-process models

    Fast Riemannian-manifold Hamiltonian Monte Carlo for hierarchical Gaussian-process models arXiv:2511.06407v1 Announce Type: new Abstract: Hierarchical Bayesian models based on Gaussian processes are considered useful for describing complex nonlinear statistical dependencies among variables in real-world data. However, effective Monte Carlo algorithms for inference with these models have not yet been established, except for several simple cases.…

  • Non-Negative Stiefel Approximating Flow: Orthogonalish Matrix Optimization for Interpretable Embeddings

    Non-Negative Stiefel Approximating Flow: Orthogonalish Matrix Optimization for Interpretable Embeddings arXiv:2511.06425v1 Announce Type: new Abstract: Interpretable representation learning is a central challenge in modern machine learning, particularly in high-dimensional settings such as neuroimaging, genomics, and text analysis. Current methods often struggle to balance the competing demands of interpretability and model flexibility, limiting their effectiveness in…

  • Prototype Selection Using Topological Data Analysis

    Prototype Selection Using Topological Data Analysis arXiv:2511.04873v1 Announce Type: new Abstract: Recently, there has been an explosion in statistical learning literature to represent data using topological principles to capture structure and relationships. We propose a topological data analysis (TDA)-based framework, named Topological Prototype Selector (TPS), for selecting representative subsets (prototypes) from large datasets. We demonstrate…

  • Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning

    Estimating Bidirectional Causal Effects with Large Scale Online Kernel Learning arXiv:2511.05050v1 Announce Type: new Abstract: In this study, a scalable online kernel learning framework is proposed for estimating bidirectional causal effects in systems characterized by mutual dependence and heteroskedasticity. Traditional causal inference often focuses on unidirectional effects, overlooking the common bidirectional relationships in real-world phenomena.…

  • A New Framework for Convex Clustering in Kernel Spaces: Finite Sample Bounds, Consistency and Performance Insights

    A New Framework for Convex Clustering in Kernel Spaces: Finite Sample Bounds, Consistency and Performance Insights arXiv:2511.05159v1 Announce Type: new Abstract: Convex clustering is a well-regarded clustering method, resembling the similar centroid-based approach of Lloyd’s $k$-means, without requiring a predefined cluster count. It starts with each data point as its centroid and iteratively merges them.…

  • QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design

    QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design arXiv:2410.07961v2 Announce Type: cross Abstract: Quantum computing is an emerging field recognized for the significant speedup it offers over classical computing through quantum algorithms. However, designing and implementing quantum algorithms pose challenges due to the complex nature of quantum mechanics and the necessity for precise control…

  • Self-adaptive weighting and sampling for physics-informed neural networks

    Self-adaptive weighting and sampling for physics-informed neural networks arXiv:2511.05452v1 Announce Type: new Abstract: Physics-informed deep learning has emerged as a promising framework for solving partial differential equations (PDEs). Nevertheless, training these models on complex problems remains challenging, often leading to limited accuracy and efficiency. In this work, we introduce a hybrid adaptive sampling and weighting…

  • Friction on Demand: A Generative Framework for the Inverse Design of Metainterfaces

    Friction on Demand: A Generative Framework for the Inverse Design of Metainterfaces arXiv:2511.03735v1 Announce Type: new Abstract: Designing frictional interfaces to exhibit prescribed macroscopic behavior is a challenging inverse problem, made difficult by the non-uniqueness of solutions and the computational cost of contact simulations. Traditional approaches rely on heuristic search over low-dimensional parameterizations, which limits…

  • Bifidelity Karhunen-Lo`eve Expansion Surrogate with Active Learning for Random Fields

    Bifidelity Karhunen-Lo`eve Expansion Surrogate with Active Learning for Random Fields arXiv:2511.03756v1 Announce Type: new Abstract: We present a bifidelity Karhunen-Lo`eve expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain inputs. The approach combines the spectral efficiency of the KLE with polynomial chaos expansions (PCEs) to preserve an explicit mapping between input uncertainties…

  • Learning Paths for Dynamic Measure Transport: A Control Perspective

    Learning Paths for Dynamic Measure Transport: A Control Perspective arXiv:2511.03797v1 Announce Type: new Abstract: We bring a control perspective to the problem of identifying paths of measures for sampling via dynamic measure transport (DMT). We highlight the fact that commonly used paths may be poor choices for DMT and connect existing methods for learning alternate…

  • A general technique for approximating high-dimensional empirical kernel matrices

    A general technique for approximating high-dimensional empirical kernel matrices arXiv:2511.03892v1 Announce Type: new Abstract: We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function $k(cdot,cdot)$. Our approach uses decoupling results for U-statistics and the non-commutative Khintchine inequality to obtain upper and lower bounds…

  • High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes

    High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes arXiv:2511.03952v1 Announce Type: new Abstract: We develop a high-dimensional scaling limit for Stochastic Gradient Descent with Polyak Momentum (SGD-M) and adaptive step-sizes. This provides a framework to rigourously compare online SGD with some of its popular variants. We show that the scaling limits of SGD-M coincide…

  • Scalable Single-Cell Gene Expression Generation with Latent Diffusion Models

    Scalable Single-Cell Gene Expression Generation with Latent Diffusion Models arXiv:2511.02986v1 Announce Type: new Abstract: Computational modeling of single-cell gene expression is crucial for understanding cellular processes, but generating realistic expression profiles remains a major challenge. This difficulty arises from the count nature of gene expression data and complex latent dependencies among genes. Existing generative models…

  • Unifying Information-Theoretic and Pair-Counting Clustering Similarity

    Unifying Information-Theoretic and Pair-Counting Clustering Similarity arXiv:2511.03000v1 Announce Type: new Abstract: Comparing clusterings is central to evaluating unsupervised models, yet the many existing similarity measures can produce widely divergent, sometimes contradictory, evaluations. Clustering similarity measures are typically organized into two principal families, pair-counting and information-theoretic, reflecting whether they quantify agreement through element pairs or aggregate…

  • Precise asymptotic analysis of Sobolev training for random feature models

    Precise asymptotic analysis of Sobolev training for random feature models arXiv:2511.03050v1 Announce Type: new Abstract: Gradient information is widely useful and available in applications, and is therefore natural to include in the training of neural networks. Yet little is known theoretically about the impact of Sobolev training — regression with both function and gradient data…

  • Provable Separations between Memorization and Generalization in Diffusion Models

    Provable Separations between Memorization and Generalization in Diffusion Models arXiv:2511.03202v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success across diverse domains, but they remain vulnerable to memorization — reproducing training data rather than generating novel outputs. This not only limits their creative potential but also raises concerns about privacy and safety. While empirical…

  • Provable Accelerated Bayesian Optimization with Knowledge Transfer

    Provable Accelerated Bayesian Optimization with Knowledge Transfer arXiv:2511.03125v1 Announce Type: new Abstract: We study how Bayesian optimization (BO) can be accelerated on a target task with historical knowledge transferred from related source tasks. Existing works on BO with knowledge transfer either do not have theoretical guarantees or achieve the same regret as BO in the…

  • Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications

    Data-driven Learning of Interaction Laws in Multispecies Particle Systems with Gaussian Processes: Convergence Theory and Applications arXiv:2511.02053v1 Announce Type: new Abstract: We develop a Gaussian process framework for learning interaction kernels in multi-species interacting particle systems from trajectory data. Such systems provide a canonical setting for multiscale modeling, where simple microscopic interaction rules generate complex…

  • DoFlow: Causal Generative Flows for Interventional and Counterfactual Time-Series Prediction

    DoFlow: Causal Generative Flows for Interventional and Counterfactual Time-Series Prediction arXiv:2511.02137v1 Announce Type: new Abstract: Time-series forecasting increasingly demands not only accurate observational predictions but also causal forecasting under interventional and counterfactual queries in multivariate systems. We present DoFlow, a flow based generative model defined over a causal DAG that delivers coherent observational and interventional…

  • Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks

    Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks arXiv:2511.02258v1 Announce Type: new Abstract: This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD) for single-layer networks. Building on the seminal work of Saad and Solla, which analyzed the deterministic (ballistic) scaling limits of SGD corresponding to the gradient flow of…