13 papers
Difficulty-Aware Semantic-ID Optimization for Generative Recommendation
Xin Yu, Stephen Li, Sina Aghaei +6
Semantic-ID-based generative recommendation casts retrieval and ranking as autoregressive generation over hierarchical item identifiers. A common recipe is SFT followed by GRPO, ye…
Q-Learning with Fine-Grained Gap-Dependent Regret
Haochen Zhang, Zhong Zheng, Lingzhou Xue
We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minima…
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
Xin Yu, Liuchen Liao, Yiwen Zhang +3
On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has…
Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
Haochen Zhang, Zhong Zheng, Lingzhou Xue
Motivated by real-world settings where data collection and policy deployment -- whether for a single agent or across multiple agents -- are costly, we study the problem of on-polic…
Gap-Dependent Bounds for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Haochen Zhang, Zhong Zheng, Lingzhou Xue
We study gap-dependent performance guarantees for nearly minimax-optimal algorithms in reinforcement learning with linear function approximation. While prior works have established…
Adaptive Algorithms for Robust Phase Retrieval
Zhong Zheng, Necdet Serhat Aybat, Shiqian Ma +1
This paper considers the robust phase retrieval, which can be cast as a nonsmooth and nonconvex composite optimization problem. We propose two first-order algorithms with adaptive…