Showing 2026Show all
2 papers · 1 filter
math.ST2026
Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
Radu Lecoiu, Debarghya Mukherjee, Pragya Sur
Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillati…
stat.ML2026
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
Conlan Olson, Linjun Zhang, Zhun Deng +1
Individual fairness, the notion that "similar individuals should be treated similarly," provides a strong and flexible fairness guarantee for algorithmic decision makers. However,…