5 papers
High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations
Youheng Zhu, Yiping Lu
High-dimensional interpolation is common in modern machine learning, but its tail risk is less understood than its expected prediction risk. Existing theory shows that interpolatin…
An AI-Assisted Solution to the Signed BAR Conjecture: Uniqueness in the Harrison--Reiman Class and a Completely- Class Obstruction
Yiping Lu, Youheng Zhu
For a multidimensional reflected diffusion, determining whether the associated basic adjoint relationship (BAR) uniquely characterizes the stationary distribution is a basic unique…
A Covering Framework for Offline POMDPs Learning using Belief Space Metric
Youheng Zhu, Yiping Lu
In off policy evaluation (OPE) for partially observable Markov decision processes (POMDPs), an agent must infer hidden states from past observations, which exacerbates both the cur…
On the Power of (Approximate) Reward Models for Inference-Time Scaling
Youheng Zhu, Yiping Lu
Inference-time scaling has recently emerged as a powerful paradigm for improving the reasoning capability of large language models. Among various approaches, Sequential Monte Carlo…
Information-theoretic Analysis of the Gibbs Algorithm: An Individual Sample Approach
Youheng Zhu, Yuheng Bu
Recent progress has shown that the generalization error of the Gibbs algorithm can be exactly characterized using the symmetrized KL information between the learned hypothesis and…