9 papers
Does Weighting Improve Matrix Factorization for Recommender Systems?
Alex Ayoub, Samuel Robertson, Dawen Liang +2
Matrix factorization is a widely used approach for top-N recommendation and collaborative filtering. When implemented on implicit feedback data (such as clicks), a common heuristic…
Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
Yaochen Zhu, Harald Steck, Dawen Liang +4
Large language models (LLMs) are reshaping the recommender system paradigm by enabling users to express preferences and receive recommendations through conversations. Yet, aligning…
DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning
Hanyang Zhao, Dawen Liang, Wenpin Tang +2
We propose DiFFPO, Diffusion Fast and Furious Policy Optimization, a unified framework for training masked diffusion large language models (dLLMs) to reason not only better (furiou…
Interacting Chern insulator transition on the sphere: revealing the Gross-Neveu-Yukawa criticality
Zhi-Qiang Gao, Taige Wang, Dung-Hai Lee
In two spatial dimensions, the transition between topological and trivial Chern insulators exemplifies a class of beyond-Landau critical phenomena. We show that the interaction-dri…
Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems
Yaochen Zhu, Chao Wan, Harald Steck +4
Conversational recommender systems (CRS) aim to provide personalized recommendations via interactive dialogues with users. While large language models (LLMs) enhance CRS with their…
Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation
Zhankui He, Zhouhang Xie, Harald Steck +4
Large language models (LLMs) are revolutionizing conversational recommender systems by adeptly indexing item content, understanding complex conversational contexts, and generating…
A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents
Kaiwen Wang, Dawen Liang, Nathan Kallus +1
We study risk-sensitive RL where the goal is learn a history-dependent policy that optimizes some risk measure of cumulative rewards. We consider a family of risks called the optim…
Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning
Alex Ayoub, Kaiwen Wang, Vincent Liu +5
We propose training fitted Q-iteration with log-loss (FQI-log) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with…
Off-Policy Evaluation for Large Action Spaces via Policy Convolution
Noveen Sachdeva, Lequn Wang, Dawen Liang +2
Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift betw…