TL;DR
The unbiased binning problem is formulating, which seeks bucketized attributes that satisfy group parity and restricts group disparities across buckets to at most πΏ -biased binning, which restricts group disparities across buckets to at most πΏ .
This paper proposes Distributional Orthogonalization Loss (DO-loss), an auxiliary regularization that shifts the focus from static weight diversity to dynamic routing behavior, and introduces the Replica Expert Mechanism (REM), which improves load balancing through a two-tiered strategy.
Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM) while controlling unfairness bias. In practice, however, fairness-aware training often yields limited improvements over standard ERM, making reliable post hoc auditing es...
This paper focuses on the k-center problem in bounded doubling metrics under two popular fairness requirements: group fairness and data summarization fairness, referred to Group Fair k-Center (Gf-k-Cen) and Data Summarization Fair k-Center (Dsf-k-Cen), respectively.
In verifier-style RLVR, group-relative optimization often treats advantage scale as an implementation detail. This paper separates two low-variance cases: sub-resolution jitter that should not become a preference signal, and credible but small cardinal gaps that should be learned without distorting KL calibration. We p...
This work proposes a decorrelation-regularized training framework that augments next-item prediction with an auxiliary redundancy-reduction term, and instantiate it with BT-SR, which uses the Barlow Twins objective to form label-consistent positive pairs without synthetic corruptions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
