Baihe Huang

sample complexity (3) zeroth-order optimization (3) large language model (2) stochastic optimization (2) gradient descent (2) offline reinforcement learning (1) sample efficiency (1) deep reinforcement learning (1) convergence analysis (1) logical reasoning (1) reinforcement learning (1) data valuation (1) label smoothing (1) reinforcement learning from human feedback (1) experimental design (1) non-convex optimization (1) model alignment (1) strongly convex (1) primal-dual algorithm (1) online learning (1)