arXiv Machine Learning
Online local learning for generative thermodynamic computing
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it 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.
arXiv Machine Learning
Jul 30
Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
arXiv:2607. 27077v1 Announce Type: new Abstract: 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.
arXiv Machine Learning
Sep 1
Emulating the Forced Response of Climate Models with Generative Machine Learning
arXiv:2605.16929v2 Announce Type: replace Abstract: Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts....
arXiv Machine Learning
Jul 7
Local Learning Rules for Out-of-Equilibrium Physical Generative Models
arXiv:2506. 19136v4 Announce Type: replace Abstract: We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules.
arXiv Machine Learning
2d ago
Training Energy-Based Models with Non-MCMC Samplers and Efficient Temperature Estimation
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.
arXiv AI
3d ago
IsingFormer: Augmenting Parallel Tempering With Learned Proposals
The paper introduces IsingFormer, a Transformer model trained on long‑run MCMC configurations, which provides global proposal moves for Parallel Tempering (PT). By integrating these learned proposals into PT—forming Transformer‑Augmented Parallel Tempering (TAPT)—the authors demonstrate lower residual energies on 3D spin‑glass instances and improved efficiency on integer factorization tasks. A scaling study shows TAPT reduces the time‑to‑solution exponent by about 33% compared to standard PT across tested problem sizes.