collaborators

6 papers

stat.ML2026

Generalization Below the Edge of Stability: The Role of Data Geometry

Tongtong Liang, Alexander Cloninger, Rahul Parhi +1

Understanding generalization in overparameterized neural networks hinges on the interplay between the data geometry, neural architecture, and training dynamics. In this paper, we t…

cs.LG2026

Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs

Hongyi Liu, Jiaji Huang, Zhen Jia +2

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding…

cs.LG2026

A second order regret bound for NormalHedge

Yoav Freund, Nicholas J. A. Harvey, Victor S. Portella +2

We consider the problem of prediction with expert advice for ``easy'' sequences. We show that a variant of NormalHedge enjoys a second-order -quantile regret bound of $O\big(\s…

cs.LG2025

Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private

Ruihan Wu, Erchi Wang, Zhiyuan Zhang +1

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time. When this corpus contains sensitive in…

cs.HC2025

DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation

Shao-Yu Chu, Yuhe Tian, Yu-Xiang Wang +1

This paper explores how programmers without specialized expertise in differential privacy (DP) (i.e., novices) can leverage LLMs to implement DP programs with minimal training. We…

cs.LG2025

No-Regret Linear Bandits under Gap-Adjusted Misspecification

Chong Liu, Dan Qiao, Ming Yin +2

This work studies linear bandits under a new notion of gap-adjusted misspecification and is an extension of Liu et al. (2023). When the underlying reward function is not linear, ex…