← Back to all news
arXiv Machine Learning By Kentaro Kubo, Hayato Goto

Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation

Read the original on arXiv Machine Learning →

The paper introduces Langevin simulated bifurcation (LSB), a fast, parallel Boltzmann sampler that matches the accuracy of sequential MCMC methods. It also proposes conditional expectation matching (CEM), an efficient technique for estimating the effective temperature of samples from energy‑based models with conditional independence. Building on these, the authors develop sampler adaptive learning (SAL), which adjusts the model temperature to align with the distribution produced by LSB, enabling efficient training of semi‑restricted Boltzmann machines (SRBMs) and outperforming conventional methods on synthetic spin‑glass datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

Hugging Face Trending Papers
Jul 29

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability. We introduce a training algorithm based on Parallel Trajectory Tempering (PTT), which exploits the continuity of the optimization path to maintain equilibrium sampling throughout learning.

multimodalbenchmarks
More like this →
arXiv Machine Learning
Aug 19

Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines

The paper introduces a new transition kernel for Restricted Boltzmann Machines that operates over the sequence of models used in Deep Tempering. This kernel employs a round‑trip structure, allowing nonlocal moves in a single transition while keeping the RBM sequence unchanged. Experiments demonstrate that it achieves higher sampling quality with fewer transitions than both blocked Gibbs sampling and Deep Tempering, and it stabilizes learning by reducing training failures.

By Kaiji Sekimoto, Muneki Yasuda
More like this →