5 papers
Annealed Langevin Monte Carlo for Flow ODE Sampling
Hanwen Huang
We propose Annealed Langevin Monte Carlo for Flow ODE Sampling (ALMC-ODE), a method for generating samples from unnormalized target distributions, with a particular emphasis on mul…
A Closed-Form Framework for Schrödinger Bridges Between Arbitrary Densities
Hanwen Huang
Score-based generative models have recently attracted significant attention for their ability to generate high-fidelity data by learning maps from simple Gaussian priors to complex…
Statistical Inference in Classification of High-dimensional Gaussian Mixture
Hanwen Huang, Peng Zeng
We consider the classification problem of a high-dimensional mixture of two Gaussians with general covariance matrices. Using the replica method from statistical physics, we invest…
Schrödinger bridge based deep conditional generative learning
Hanwen Huang
Conditional generative models represent a significant advancement in the field of machine learning, allowing for the controlled synthesis of data by incorporating additional inform…
One-step data-driven generative model via Schrödinger Bridge
Hanwen Huang
Generating samples from a probability distribution is a fundamental task in machine learning and statistics. This article proposes a novel scheme for sampling from a distribution f…