Daniel M. Roy

Latest

• Relaxing the I.I.D. Assumption: Adaptively Minimax Optimal Regret via Root-Entropic Regularization
• Minimax Rates for Conditional Density Estimation via Empirical Entropy
• Adaptively Exploiting d-Separators with Causal Bandits
• Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers
• Tight Bounds on Minimax Regret Under Logarithmic Loss via Self-Concordance