Zichong Li

reinforcement learning from human feedback (2) reward learning (2) augmented lagrangian method (2) event sequence (2) black-box optimization (1) uncertainty quantification (1) direct preference optimization (1) preference optimization (1) composite optimization (1) language model alignment (1) deep learning (1) outlier detection (1) point process (1) score matching (1) robust learning (1) distributionally robust optimization (1) complexity bound (1) zeroth-order optimization (1) first-order method (1) confidence interval (1)