Yuanyu Wan

KeepLoRA: Continual Learning with Residual Gradient Adaptation

Multi-Objective Bandits with Hierarchical Preferences: A Thompson Sampling Approach

Continuous Subspace Optimization for Continual Learning

Multi-objective Linear Reinforcement Learning with Lexicographic Rewards

Dimension-Free Adaptive Subgradient Methods with Frequent Directions

Revisiting Differentially Private Algorithms for Decentralized Online Learning

Is the Fairness Metric Truly Fair?