Beyond Discrepancy: Oracle Drift in Nonstationary Weighted Risk Minimization

math.ST, stat.ML, stat.TH

Submitted: 2026-10-09

Updated: 2026-10-09

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Generalization bounds for nonparametric regression with $\beta-$mixing samples
• Fast Rates for Nonstationary Weighted Risk Minimization
• Trade-off Between Dependence and Complexity for Nonparametric Learning -- an Empirical Process Approach
• Optimal Empirical Risk Minimization under Temporal Distribution Shifts
• Don't Look Back in Anger: Wasserstein Distributionally Robust Optimization with Nonstationary Data
• On Localized Discrepancy for Domain Adaptation

Related papers

• Conformal Prediction for Dyadic Regression Under Complex Missingness
• Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
• Bentkus-type asymptotic e-values
• High-Dimensional Asymptotics of Differentially Private PCA
• A proximal gradient algorithm for composite log-concave sampling
• KL Convergence Guarantees for Score diffusion models under minimal data assumptions