5 papers
ExpBoN: Exponential-Noise Best-of- for Efficient Test-Time LLM Alignment
Yanxiao Liu, Sicheng Wan, Deniz Gündüz
Best-of- (BoN) sampling is a simple yet effective inference-time alignment method, but hard maximization provides only coarse control over the trade-off between reward and distr…
Watermarkable Multi-Draft Speculative Sampling via Poisson Processes
Yanxiao Liu, Sicheng Wan, Zhan Gao +1
Large language models (LLMs) have achieved state-of-the-art performance across a wide range of tasks, motivating two important aspects of deployment: inference efficiency and outpu…
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
Gergely Flamich, Oykü Sıla Güner, Yanxiao Liu +1
The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual identity. Differential privacy (D…
Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
Yanxiao Liu, Yijun Fan, Deniz Gündüz
Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic…
On the Generalization Error of Differentially Private Algorithms via Typicality
Yanxiao Liu, Chun Hei Michael Shiu, Lele Wang +1
We study the generalization error of stochastic learning algorithms from an information-theoretic perspective, with a particular emphasis on deriving sharper bounds for differentia…