Gibbs

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 27

All topics

Fixed-point neural samplers on discrete spaces
Oct 1, 2026Jiajun He, Denis Blessing, Mouyang Cheng +2Accelerated Sampling Gibbs
MIT · Microsoft Research New England
An analysis of Mirror-Descent Soft Actor-Critic
Sep 28, 2026Denis Zorba, Michal ValkoMirror Descent Soft Actor-Critic
School of Mathematics, University of Edinburgh, United Kingdom · INRIA, Paris, France
Machine Unlearning for Gibbs Supervised Learning Algorithms
Sep 24, 2026Yaiza Bermudez, Samir M. Perlaza, Iñaki EsnaolaGibbs Exact Unlearning
Centre Inria d’Universit´e Cˆote d’Azur, INRIA, Sophia Antipolis, France. · Laboratoire GAATI, Universit´e de la Polyn´esie franc¸aise, Fa‘a‘¯a, French Polynesia. · ECE Dept. Princeton University, Princeton, 08544 NJ, USA. +1
Particle GFlowNets: Rethinking Generative Marginalization Models
Sep 11, 2026Tiago da Silva, Diego Mesquita, Salem LahlouGenerative Flow Networks Gibbs
MBZUAI · School of Applied Mathematics, Getulio Vargas Foundation
Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs
Jul 30, 2026Borna Khodabandeh, Mehdi MolkaraieProbabilistic Graphical Models Gibbs
Department of Statistics, University of Oxford, Oxford OX1 3LB, UK · Department of Signal Theory and Communications, UPC, 08034 Barcelona, Spain · Department of Statistical Sciences, University of Toronto, ON M5G 1X6, Canada
Machine-Learned Compact Subspace Generation for Quantum Selected Configuration Interaction within Density Matrix Embedding Framework
Jul 22, 2026Ashish Kumar Patra, Anurag K. S. V., Ruchika Bhat +3Quantum Chemistry Density Functional Theory
1Qclairvoyance Quantum Labs, Secunderabad, TG 500094, India. · 2The University of Arizona, Tucson, AZ 85721, USA. · 3Indian Institute of Technology Bombay, Mumbai, MH 400076, India.
Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems
Jul 13, 2026Ke Sun, Xinyuan Zhang, Xinwu QianSalesman Problem Construction
Department of Civil and Environmental Engineering, Rice University, Houston, TX
Nonparametric Bayesian Inverse Reinforcement Learning with Data-Parallel Gibbs Sampling
Jul 10, 2026Sai Anirudh Katupilla, Shreeya Dasa LakshminathGibbs Offline Reinforcement Learning
University of Maryland, College Park
Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures
Jun 29, 2026L. U. Abdullaev, F. Herrera, U. A. Rozikov +1Gibbs Transition Learning
National University of Singapore, Singapore · Department of Computer Science and Artificial Intelligence, University of Granada, E-18071 Granada, Spain · V.I. Romanovskiy Institute of Mathematics, Uzbekistan Academy of Sciences, 9, Universitet str., 100174, Tashkent, Uzbekistan +3
A Tool for the Synthesis of Adaptive Probabilistic Processors Based on the Ising Model
Jun 17, 2026Jonathan Juracy Carneiro da Silva, Leonardo R. Gobatto, Jose Rodrigo AzambujaGibbs Quantum Annealing
Federal University of Rio Grande do Sul (UFRGS) – Institute of Informatics – PGMicro, Porto Alegre, Brazil · Center for Embedded Devices and Research in Digital Agriculture (CEDRA), S˜ao Leopoldo, Brazil
Structured Inference with Large Language Gibbs
Jun 17, 2026Sanghyeok Choi, Henry Gouk, Esmeralda S. WhitammerProbabilistic Inference LLM Reasoning Strategies
University of Edinburgh, School of Informatics · 2CIFAR Fellow, Learning in Machines and Brains
Conformal Candidate Certification for Offline Model-Based Optimization
Jun 13, 2026Seungjin ChoiOnline Conformal Prediction Candidate
CROID Research and aSSIST University, Seoul, Korea.
Regularized Large Neighborhood Search
Jun 1, 2026Germain Vivier-Ardisson, Laurent Demonet, Axel Parmentier +1Neural Combinatorial Optimization Large Neighborhood Search
Google DeepMind & CERMICS · Google Research · CERMICS, ENPC, CNRS, IPP +1
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
May 29, 2026Xiaoyu Wang, Jonathan H. HugginsVariational Inference Gibbs
Department of Mathematics & Statistics, Boston University · Faculty of Computing & Data Sciences, Boston University
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
May 24, 2026Yudong W. Xu, Wenhao Li, Xiaoyu Wang +2Constraint Satisfaction Diffusion Transformers
University of Toronto · Vector Institute
Reinforcement Learning for Graph Generation under a Hard Assortativity Constraint
May 22, 2026Hoyun Choi, Junghyo Jo, Deok-Sun LeeInhomogeneous Random Graphs Network Science
School of Computational Sciences, Korea Institute for Advanced Study, 85, Hoegi-ro, 02455, Seoul, Korea. · Department of Physics Education, Seoul National University, 1, Gwanak-ro, 08826, Seoul, Korea. · Center for Theoretical Physics and Artificial Intelligence Institute, Seoul National University, 1, Gwanak-ro, 08826, Seoul, Korea. +1
Canonical Regularisation of Wide Feature-Learning Neural Networks
May 18, 2026George Whittle, Pranav Vaidhyanathan, Juliusz Ziomek +2Feature Learning Regularization
Department of Engineering Science University of Oxford
Anytime PAC-Bayes for Constrained Density-Ratio Networks under Covariate Shift
May 17, 2026Paulo Akira F. Enabe, Rodrigo ProvasiCovariate Shift Pac-Bayesian Theory
Escola Politénica University of São Paulo Department of Structural and Geotechnical Engineering
$h$ -control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
May 12, 2026Yuzhu Wang, Xi Ye, Duo Su +2Camera Control Camera-Conditioned Video Generation
Department of Computer Science and Technology, Tsinghua University · South China University of Technology
Composing diffusion priors with explicit physical context via generative Gibbs sampling
May 11, 2026Weizhou Wang, Jonathan Weare, Aaron R. DinnerGibbs Diffusion Priors
Department of Chemistry University of Chicago Chicago, IL 60637 · Courant Institute of Mathematical Sciences New York University New York, NY 10012
Decentralized Proximal Stochastic Gradient Langevin Dynamics
May 1, 2026Mohammad Rafiqul Islam, Lingjiong ZhuGibbs Markov Chain Monte Carlo
Department of Mathematics, Florida State University, Tallahassee, Florida, United States of America
Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms
Apr 22, 2026Yaiza Bermudez, Samir M. Perlaza, Iñaki EsnaolaDecentralized Learning Gibbs
Centre Inria d'Université Côte d'Azur, INRIA, Sophia Antipolis, France. · Laboratoire GAATI, Université de la Polynésie française, Fa'a'ā, French Polynesia. · ECE Dept. Princeton University, Princeton, 08544 NJ, USA. +1
A Gibbs posterior sampler for inverse problem based on prior diffusion model
Feb 11, 2026Jean-François GiovannelliPosterior Sampling Gibbs
Groupe Signal-Image, IMS (Univ. Bordeaux, CNRS, BINP), Talence, France
Gibbs randomness-compression proposition
May 29, 2025M. SüzenGibbs Random
The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms
Nov 18, 2024Samir M. Perlaza, Xinying ZouGeneralization Bounds Empirical Risk Minimization
INRIA, Centre Inria d’Universit´e Cˆote d’Azur, 06902 Sophia Antipolis, France
Discrete distributions are learnable from metastable samples
Oct 17, 2024Abhijith Jayakumar, Andrey Y. Lokhov, Sidhant Misra +1Metastable Samples Gibbs
Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USA
Monte Carlo with kernel-based Gibbs measures: Guarantees for probabilistic herding
Feb 18, 2024Martin Rouault, Rémi Bardenet, Mylène MaïdaGibbs Bayesian Quadrature
1Univ. Lille, CNRS, Centrale Lille, UMR 9189 – CRIStAL, 59651 Villeneuve d’Ascq, France · 2Univ. Lille, CNRS, UMR 8524 – Laboratoire Paul Painlev´e, F-59000 Lille, France

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Fixed-point neural samplers on discrete spaces

Jiajun He, Denis Blessing, Mouyang Cheng, Yuanqi Du+1

MIT · Microsoft Research New England

Accelerated Sampling Gibbs Generative Models

Open paper AskPDF arXiv

Sampling from discrete, unnormalized distributions without access to data is a challenging problem. Neural samplers offer a promising approach by training generative models from density evaluations directly. Despite recent progress, existing discrete neural samplers are prone to mode collapse, come without convergence guarantees when trained via fixed-point iterations, and are often tied to a specific reference process such as masked or uniform diffusion. In this work, we introduce Discrete Gibbs Iterative Neural Sampler, a fixed-point neural sampler that addresses these limitations, enabling efficient, scalable learning, substantially reducing mode collapse in practice. Our framework builds on masked diffusion and also extends to transport between pairs of distributions. We demonstrate that the resulting method scales effectively to high-dimensional systems, supports amortized sampling across different conditions, and enables accurate estimation of alloy phase diagrams.

Momentum

Related topics

Latest papers 27