4 papers
Memory--Batch Tradeoffs in Lipschitz Bandits
Zicheng Lyu, Zengfeng Huang
Lipschitz bandits admit near-optimal regret with little memory under full adaptivity, or with few batches under unrestricted memory. We characteri…
ReMath: Benchmarking Theorem Retrieval in Research-Level Mathematics
Zicheng Lyu, Wenjie Yang, Shengzhong Zhang +1
Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof rea…
Few Batches or Little Memory, But Not Both: Simultaneous Space and Adaptivity Constraints in Stochastic Bandits
Ruiyuan Huang, Zicheng Lyu, Xiaoyi Zhu +1
We study stochastic multi-armed bandits under simultaneous constraints on space and adaptivity: the learner interacts with the environment in batches and has only bits of p…
Load--Reserve Wasserstein Propagation for Isotropic Diffusion Samplers
Zicheng Lyu, Zengfeng Huang
Many Wasserstein analyses of diffusion samplers control reverse-time propagation by global stability summaries of the learned drift. These summaries can hide radial geometry: equal…