FrOGS is a hybrid discrete neural sampler that couples an autoregressive model with a continuous-time Markov chain, trained under a single shared loss to sample alloy configurations across many chemical conditions. It produces independent, unbiased configurations, estimates the partition function, and yields consistent thermodynamic observables on a common absolute free‑energy scale. The method matches exact results for the 2D Ising model and reproduces reference phase diagrams for AgPd and CuAu, avoiding mode collapse and correctly recovering the stability range of the CuAu$_3$ phase.
By Kyucheol Min, Elyssa Hofgard, Tess Smidt
arXiv:2609.15894v1 Announce Type: cross
Abstract: Some of the sharpest challenges in sampling from the energy functions of physical systems arise at phase transitions, where the density of states cha...
By David Yallup
The paper investigates training diffusion models to sample from distributions defined by unnormalized densities or energy functions. It benchmarks various diffusion-structured inference techniques, including simulation-based variational methods and off-policy approaches such as continuous generative flow networks, highlighting their relative strengths and challenging some prior claims. Additionally, the authors introduce a new exploration strategy for off-policy methods that employs local search in the target space with a replay buffer, demonstrating improved sample quality across multiple target distributions.
By Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Esmeralda S. Whitammer
The paper introduces Particle GFlowNets, showing that Generative Marginalization Models (MaMs) are equivalent to Generative Flow Networks. It extends MaMs to non‑autoregressive sampling and proposes an automatic full‑state rejuvenation criterion based on the Gelman‑Rubin statistic to accelerate learning. Experiments demonstrate significant training speedups in large combinatorial spaces.
By Tiago da Silva, Diego Mesquita, Salem Lahlou
arXiv:2608. 07648v1 Announce Type: cross Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to statistical physics and molecular simulation.
By Marylou Gabri\'e
arXiv:2410.01432v3 Announce Type: replace
Abstract: Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized d...
By Minsu Kim, Sanghyeok Choi, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Esmeralda S. Whitammer, Yoshua Bengio
The paper introduces a learning-based approach to replace the MCMC step in split-Gibbs diffusion posterior sampling. By reformulating both Gibbs updates as Gaussian denoising problems, the method uses ODE diffusion for the prior step with a pretrained denoiser and a lightweight deep-unfolded network for the likelihood step. Experiments on nonlinear phase retrieval show that this alternative reduces likelihood-update cost while maintaining effectiveness compared to MCMC-based split Gibbs.
By Yi Zhang, Rui Guo, Mengchu Xu, Zhaofeng Liu, Yonina C. Eldar
arXiv:2506. 13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation.
By Hu Yu, Hao Luo, Xueyang Fu, Jie Huang, Fan Wang, Feng Zhao
arXiv:2512. 16607v2 Announce Type: replace-cross Abstract: Sampling configurations in thermodynamic equilibrium is a long-standing challenge in statistical physics.
By Louis Grenioux, Leonardo Galliano, Ludovic Berthier, Giulio Biroli, Marylou Gabri\'e
arXiv:2606. 30773v1 Announce Type: cross Abstract: We introduce a novel technique for scalable sampling of spin-system states with continuous symmetries using diffusion models.
By Sehmimul Hoque, Roger Melko, Pooya Ronagh
arXiv:2606. 16073v1 Announce Type: new Abstract: Sampling from complex, unnormalized probability densities is a fundamental challenge in Bayesian inference and probabilistic modeling.
By Kirill Korolev, Nikita Morozov, Stepan Pavlenko, Esmeralda S. Whitammer, Sergey Samsonov
arXiv:2606. 13796v1 Announce Type: cross Abstract: Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution.
By Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan