Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
Chenyang Wang, Weizhong Wang, Yinuo Ren +2
iffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific obj…
stat.ML2026
PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory
Chenyang Wang, Yun Yang
We derive explicit non-asymptotic PAC-Bayes generalization bounds for Gibbs posteriors, that is, data-dependent distributions over model parameters obtained by exponentially tiltin…