Yu-Jie Zhang

dynamic regret (6) online learning (4) online convex optimization (3) regret bound (3) distribution shift (2) stochastic optimization (2) gradient variation (2) domain adaptation (2) unbiased risk estimator (2) non-stationary environment (2) imitation learning (1) supervised learning (1) policy learning (1) feature disentanglement (1) preference learning (1) reinforcement learning (1) function approximation (1) covariate shift (1) convex optimization (1) semi-supervised learning (1)