paper-with-me

홈 › Papers

BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching

2024-09-15 · Ruikang Ouyang, Bo Qiang, José Miguel Hernández-Lobato

Developing an efficient sampler capable of generating independent and identically distributed (IID) samples from a Boltzmann distribution is a crucial challenge in scientific research, e.g. molecular dynamics. In this work, we intend to learn neural samplers given energy functions instead of data sampled from the Boltzmann distribution. By learning the energies of the noised data, we propose a diffusion-based sampler, Noised Energy Matching, which theoretically has lower variance and more complexity compared to related works. Furthermore, a novel bootstrapping technique is applied to NEM to balance between bias and variance. We evaluate NEM and BNEM on a 2-dimensional 40 Gaussian Mixture Model (GMM) and a 4-particle double-well potential (DW-4). The experimental results demonstrate that BNEM can achieve state-of-the-art performance while being more robust.

📄 PDF Abstract BibTeX arXiv:2409.09787

Code (1)

tonyauyeung/BNEM 공식 구현 pytorch

Tasks

Denoising

Similar Papers 제목 키워드 기반

One-Step Sampler for Boltzmann Distributions via Drifting

2026-03-18 · Wenhan Cao, Keyu Yan, Lin Zhao arxiv

We present a drifting-based framework for amortized sampling of Boltzmann distributions defined by energy functions. The method trains a one-step neural generator by projecting samples along a Gaussian-smoothed score fie…

Boltzmann machines and energy-based models

2017-08-20 · Takayuki Osogami

We review Boltzmann machines and energy-based models. A Boltzmann machine defines a probability distribution over binary-valued patterns. One can learn parameters of a Boltzmann machine via gradient based approaches in a…

Unlocking the Power of Boltzmann Machines by Parallelizable Sampler and Efficient Temperature Estimation

2025-12-02 · Kentaro Kubo, Hayato Goto arxiv

Boltzmann machines (BMs) are powerful energy-based generative models, but their heavy training cost has largely confined practical use to Restricted BMs (RBMs) trained with an efficient learning method called contrastive…

Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange

2025-01-28 · Haoyang Zheng, Hengrong Du, Ruqi Zhang, Guang Lin

Gradient-based Discrete Samplers (GDSs) are effective for sampling discrete energy landscapes. However, they often stagnate in complex, non-convex settings. To improve exploration, we introduce the Discrete Replica EXcha…

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

2021-02-08 · Will Grathwohl, Kevin Swersky, Milad Hashemi, David Duvenaud 외

We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose upda…