mailitics

Tag: sensitive

  • Doubly-Regressing Approach for Subgroup Fairness

    Doubly-Regressing Approach for Subgroup Fairness arXiv:2510.21091v1 Announce Type: new Abstract: Algorithmic fairness is a socially crucial topic in real-world applications of AI. Among many notions of fairness, subgroup fairness is widely studied when multiple sensitive attributes (e.g., gender, race, age) are present. However, as the number of sensitive attributes grows, the number of subgroups increases…

  • Lower Bounds on the MMSE of Adversarially Inferring Sensitive Features

    Lower Bounds on the MMSE of Adversarially Inferring Sensitive Features arXiv:2505.09004v1 Announce Type: new Abstract: We propose an adversarial evaluation framework for sensitive feature inference based on minimum mean-squared error (MMSE) estimation with a finite sample size and linear predictive models. Our approach establishes theoretical lower bounds on the true MMSE of inferring sensitive features…

  • Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics

    Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics arXiv:2505.06435v1 Announce Type: new Abstract: AI fairness, also known as algorithmic fairness, aims to ensure that algorithms operate without bias or discrimination towards any individual or group. Among various AI algorithms, the Fair Representation Learning (FRL) approach has gained significant interest in…

  • Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms

    Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms arXiv:2503.08896v1 Announce Type: new Abstract: This paper introduces a general framework for risk-sensitive bandits that integrates the notions of risk-sensitive objectives by adopting a rich class of distortion riskmetrics. The introduced framework subsumes the various existing risk-sensitive models. An important and hitherto unknown observation is that for…

  • Efficient Risk-sensitive Planning via Entropic Risk Measures

    Efficient Risk-sensitive Planning via Entropic Risk Measures arXiv:2502.20423v1 Announce Type: new Abstract: Risk-sensitive planning aims to identify policies maximizing some tail-focused metrics in Markov Decision Processes (MDPs). Such an optimization task can be very costly for the most widely used and interpretable metrics such as threshold probabilities or (Conditional) Values at Risk. Indeed, previous work…