mailitics

Tag: domain

  • Anti-causal domain generalization: Leveraging unlabeled data

    Anti-causal domain generalization: Leveraging unlabeled data arXiv:2602.17187v1 Announce Type: new Abstract: The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training environments, limiting their applicability when labeled data are scarce. In this work, we…

  • 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…

  • Domain-Shift-Aware Conformal Prediction for Large Language Models

    Domain-Shift-Aware Conformal Prediction for Large Language Models arXiv:2510.05566v1 Announce Type: new Abstract: Large language models have achieved impressive performance across diverse tasks. However, their tendency to produce overconfident and factually incorrect outputs, known as hallucinations, poses risks in real world applications. Conformal prediction provides finite-sample, distribution-free coverage guarantees, but standard conformal prediction breaks down under…

  • Unsupervised Domain Adaptation with an Unobservable Source Subpopulation

    Unsupervised Domain Adaptation with an Unobservable Source Subpopulation arXiv:2509.20587v1 Announce Type: new Abstract: We study an unsupervised domain adaptation problem where the source domain consists of subpopulations defined by the binary label $Y$ and a binary background (or environment) $A$. We focus on a challenging setting in which one such subpopulation in the source domain…

  • A Unified Analysis of Generalization and Sample Complexity for Semi-Supervised Domain Adaptation

    A Unified Analysis of Generalization and Sample Complexity for Semi-Supervised Domain Adaptation arXiv:2507.22632v1 Announce Type: new Abstract: Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels. While the field has seen extensive methodological development, its theoretical foundations remain relatively underexplored.…

  • On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective

    On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective arXiv:2507.06552v1 Announce Type: new Abstract: This paper studies the hardness of unsupervised domain adaptation (UDA) under covariate shift. We model the uncertainty that the learner faces by a distribution $pi$ in the ground-truth triples $(p, q, f)$ — which we call a UDA…

  • What is your domain and what are the most important technical skills that help you stand out in your domain?

    What is your domain and what are the most important technical skills that help you stand out in your domain? Aside from soft skills and domain expertise, ofc those are a given. I’m manufacturing-adjacent (closer to product development and validation). Design of experiments has been my most useful data-related skill. I’m always being asked “We…

  • Continuous Domain Generalization

    Continuous Domain Generalization arXiv:2505.13519v1 Announce Type: new Abstract: Real-world data distributions often shift continuously across multiple latent factors such as time, geography, and socioeconomic context. However, existing domain generalization approaches typically treat domains as discrete or evolving along a single axis (e.g., time), which fails to capture the complex, multi-dimensional nature of real-world variation. This…

  • Optimal Transport-Based Domain Adaptation for Rotated Linear Regression

    Optimal Transport-Based Domain Adaptation for Rotated Linear Regression arXiv:2505.09229v1 Announce Type: new Abstract: Optimal Transport (OT) has proven effective for domain adaptation (DA) by aligning distributions across domains with differing statistical properties. Building on the approach of Courty et al. (2016), who mapped source data to the target domain for improved model transfer, we focus…

  • DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization

    DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization arXiv:2503.23430v1 Announce Type: new Abstract: Domain generalization (DG) aims to learn models that can generalize well to unseen domains by training only on a set of source domains. Sharpness-Aware Minimization (SAM) has been a popular approach for this, aiming to find flat minima in the total loss landscape.…

  • Transfer Learning through Enhanced Sufficient Representation: Enriching Source Domain Knowledge with Target Data

    Transfer Learning through Enhanced Sufficient Representation: Enriching Source Domain Knowledge with Target Data arXiv:2502.20414v1 Announce Type: new Abstract: Transfer learning is an important approach for addressing the challenges posed by limited data availability in various applications. It accomplishes this by transferring knowledge from well-established source domains to a less familiar target domain. However, traditional transfer…

  • Injecting domain expertise into your AI system

    Injecting domain expertise into your AI system How to connect the dots between AI technology and real life (Source: Getty Images) When starting their AI initiatives, many companies are trapped in silos and treat AI as a purely technical enterprise, sidelining domain experts or involving them too late. They end up with generic AI applications that miss…

  • Statistical Inference for Sequential Feature Selection after Domain Adaptation

    Statistical Inference for Sequential Feature Selection after Domain Adaptation arXiv:2501.09933v1 Announce Type: new Abstract: In high-dimensional regression, feature selection methods, such as sequential feature selection (SeqFS), are commonly used to identify relevant features. When data is limited, domain adaptation (DA) becomes crucial for transferring knowledge from a related source domain to a target domain, improving…

  • On Robust Cross Domain Alignment

    On Robust Cross Domain Alignment arXiv:2412.15861v1 Announce Type: new Abstract: The Gromov-Wasserstein (GW) distance is an effective measure of alignment between distributions supported on distinct ambient spaces. Calculating essentially the mutual departure from isometry, it has found vast usage in domain translation and network analysis. It has long been shown to be vulnerable to contamination…