8 papers
Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels
Fairoz Nower Khan, Nabuat Zaman Nahim, Md Sajid Ahmed +2
MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity field of flow matching. Howeve…
Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs
Ruiquan Huang, Donghao Li, Yingbin Liang +1
Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment.…
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis
Ruiquan Huang, Donghao Li, Chengshuai Shi +2
This paper investigates a hybrid learning framework for reinforcement learning (RL) in which the agent can leverage both an offline dataset and online interactions to learn the opt…
How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
Ruiquan Huang, Yingbin Liang, Jing Yang
Language recognition tasks are fundamental in natural language processing (NLP) and have been widely used to benchmark the performance of large language models (LLMs). These tasks…
Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
Ruiquan Huang, Yingbin Liang, Jing Yang
Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline data…
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Ruiquan Huang, Yingbin Liang, Jing Yang
Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) task…