Xueying LI

representation learning (1) policy evaluation (1) off-policy evaluation (1) offline reinforcement learning (1) embedding learning (1) prototype learning (1) collaborative filtering (1) noisy label learning (1) knowledge distillation (1) policy learning (1) submodular maximization (1) semantic similarity (1) approximation algorithm (1) parallel algorithm (1) sequential recommendation (1) recommendation system (1) open-set recognition (1) budget constraint (1) click-through rate (1) lagrangian multiplier (1)