8 papers
Oracle-Efficient and Parameter-Free Agnostic Smoothed Online Learning
Sasha Voitovych, Adam Block, Alexander Rakhlin +1
Online learning is an attractive framework in many domains because it permits well-defined learning even when data are dependent or chosen adversarially. This generality, however,…
From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism
Zhuohao Yu, Zhiwei Steven Wu, Adam Block
Inference-time compute scaling has emerged as a powerful paradigm for improving language model performance on a wide range of tasks, but the question of how best to use the additio…
Partition Function Estimation under Bounded f-Divergence
Adam Block, Abhishek Shetty
We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio for a target distribution. Wh…
MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
Yizhou Zhao, Zhiwei Steven Wu, Adam Block
Language model watermarking schemes fall into two broad categories: inference-time methods, which modify the decoding process at generation time, and model-embedded methods, which…
Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective
Adam Block, Abhishek Shetty
In order to develop practical and efficient algorithms while circumventing overly pessimistic computational lower bounds, recent work has been interested in developing oracle-effic…
GaussMark: A Practical Approach for Structural Watermarking of Language Models
Adam Block, Ayush Sekhari, Alexander Rakhlin
Recent advances in Large Language Models (LLMs) have led to significant improvements in natural language processing tasks, but their ability to generate human-quality text raises s…
On the Performance of Empirical Risk Minimization with Smoothed Data
Adam Block, Alexander Rakhlin, Abhishek Shetty
In order to circumvent statistical and computational hardness results in sequential decision-making, recent work has considered smoothed online learning, where the distribution of…
Oracle-Efficient Differentially Private Learning with Public Data
Adam Block, Mark Bun, Rathin Desai +2
Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the perf…