Daniel M Roy

Latest

• Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers
• Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics
• In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors
• Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
• Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates