4 papers
Simple and Sharp Generalization Bounds via Lifting
Jingbo Liu
We develop an information-theoretic framework for bounding the supremum of stochastic processes, offering a simpler and sharper alternative to classical chaining and slicing argume…
Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures
Zhiyuan Yu, Jingbo Liu
Approximate inference is central to Bayesian learning, with variational inference (VI) providing a scalable framework for posterior approximation. While mean-field VI often fails i…
A Black-Box Debiasing Framework for Conditional Sampling
Han Cui, Jingbo Liu
Conditional sampling is a fundamental task in Bayesian statistics and generative modeling. Consider the problem of sampling from the posterior distribution for some o…
Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold
Han Cui, Zhiyuan Yu, Jingbo Liu
Recently, Approximate Message Passing (AMP) has been integrated with stochastic localization (diffusion model) by providing a computationally efficient estimator of the posterior m…