Energy based diffusion generator for efficient sampling of Boltzmann distributions
School of Mathematical Sciences, Tongji University(同济大学数学科学学院);Department of Mathematics, Shanghai Normal University(上海师范大学数学系);Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)
Sampling from Boltzmann distributions, particularly those tied to high dimensional and complex energy functions, poses a significant challenge in many fields. In this work, we present the Energy-Based Diffusion Generator (EDG), a novel approach that integrates ideas from variational autoencoders and diffusion models. EDG uses a decoder to generate Boltzmann-distributed samples from simple latent variables, and a diffusion-based encoder to estimate the Kullback-Leibler divergence to the target distribution. Notably, EDG is simulation-free, eliminating the need to solve ordinary or stochastic differential equations during training. Furthermore, by removing constraints such as bijectivity in the decoder, EDG allows for flexible network design. Through empirical evaluation, we demonstrate the superior performance of EDG across a variety of sampling tasks with complex target distributions, outperforming existing methods.
Transition Path Sampling with Boltzmann Generator-based MCMC Moves
School of Computation, Information and Technology, TUM(慕尼黑工业大学计算、信息与技术学院);Computer Science and Artificial Intelligence Laboratory, MIT(麻省理工学院计算机科学与人工智能实验室);Department of Computer Science, ETH Zürich(苏黎世联邦理工学院计算机科学系)
Institute of Nanotechnology, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院纳米技术研究所);Institute of Theoretical Informatics, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院理论计算机科学研究所)
Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
State Key Laboratory of Information Photonics(信息光子学与光通信国家重点实验室);Optical Communications, Beijing University of Posts(光通信,北京邮电大学);School of Physical Science(物理科学学院);Technology, Beijing University of Posts(技术学院,北京邮电大学)
Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators
Mila – Québec AI Institute(魁北克AI研究所);Université de Montréal(蒙特利尔大学);Massachusetts Institute of Technology(麻省理工学院);University of Oxford(牛津大学);AITHYRA;HEC Montréal(蒙特利尔HEC)
GM Score: Incorporating inter-class and intra-class generator diversity, discriminability of disentangled representation, and sample fidelity for evaluating GANs
School of Computer Engineering, KIIT Deemed to be University(KIIT 大学计算机工程学院)
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
McGill University(麦吉尔大学);Mila – Quebec AI Institute(魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);University of Oxford(牛津大学);Google DeepMind(谷歌DeepMind);AITHYRA;Valence Labs(Valence实验室);Institut Courtois(Courtois研究所)
Boltzmann generators for amorphous particle systems
Laboratoire de Physique de l’École normale supérieure ENS, Université PSL, CNRS, Sorbonne Université, Université de Paris(巴黎高等师范学院物理实验室,巴黎科学研究院,法国国家科学研究中心,索邦大学,巴黎大学);CMAP, CNRS, École polytechnique, Institut Polytechnique de Paris(巴黎高等理工学院计算数学与应用物理实验室,法国国家科学研究中心,巴黎理工学院,巴黎理工研究院);Dipartimento di Fisica, Università di Trieste(特伦蒂诺-上阿迪杰大学物理系);Gulliver, CNRS UMR 7083, ESPCI Paris, PSL Research University(Gulliver,法国国家科学研究中心UMR 7083,巴黎高等师范学院,巴黎科学研究院)
Professorship of Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich, Germany(多尺度流体材料建模教授职位,工程物理与计算系,TUM工程与设计学院,慕尼黑技术大学,德国);Atomistic Modeling Center, Munich Data Science Institute, Technical University of Munich, Germany(原子建模中心,慕尼黑数据科学研究所,慕尼黑技术大学,德国)
University of Toronto(多伦多大学);NVIDIA(英伟达);Vector Institute(向量研究所);ETH Zurich(苏黎世联邦理工学院);NCCR Catalysis(瑞士国家研究能力中心催化分部);Acceleration Consortium(加速联盟);CIFAR(加拿大高等研究院)
Quantum-inspired annealers as Boltzmann generators for machine learning and statistical physics
Russian Quantum Center(俄罗斯量子中心);Moscow Institute of Physics and Technology(莫斯科物理技术学院);University of Oxford(牛津大学);P. N. Lebedev Physics Institute(P. N. 列别杰夫物理研究所)
Learning Boltzmann Generators via Constrained Mass Transport
Autonomous Learning Robots, Karlsruhe Institute of Technology(自动化学习机器人,卡尔斯鲁厄大学技术学院);Artificial Intelligence for Materials Sciences, Karlsruhe Institute of Technology(材料科学人工智能,卡尔斯鲁厄大学技术学院)
Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
Microsoft Research AI for Science(微软研究院人工智能科学部门);Department of Chemistry, Rice University(理查德·伊尔大学化学系);Initiative for Computational Catalysis, Flatiron Institute(计算催化倡议,Flatiron研究所)
Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
Institute of Nanotechnology, Karlsruhe Institute of Technology, Kaiserstr. 12, 76131 Karlsruhe, Germany(纳米技术研究所,卡尔斯鲁厄理工大学,Kaiserstr. 12,76131 卡尔斯鲁厄,德国);Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Kaiserstr. 12, 76131 Karlsruhe, Germany(人机学与机器人研究所,卡尔斯鲁厄理工大学,Kaiserstr. 12,76131 卡尔斯鲁厄,德国)
Barriers and Dynamical Paths in Alternating Gibbs Sampling of Restricted Boltzmann Machines
Laboratory of Physics of the \'Ecole Normale Sup\'erieure, CNRS UMR 8023 \& PSL Research, Sorbonne Universit\'e, 24 rue Lhomond, 75005 Paris, France
受限玻尔兹曼机(RBM)是一种双层神经网络,用于从数据中无监督地学习模型分布。RBM的二分体系结构自然定义了一个优雅的采样过程,称为交替吉布斯采样(AGS),其中潜变量层的配置被采样为数据变量层的条件,反之亦然。我们在这里研究的性能AGS几个分析听话的模型借用统计力学。我们表明,标准的AGS是不是更有效的比经典的大都会黑斯廷斯(MH)采样的有效能源景观上定义的数据层。然而,RBM可以识别训练数据在其潜在空间中的有意义的表示。此外,使用这些表示,并结合吉布斯采样与MH算法在潜在的空间可以提高RBM的采样性能时,隐藏单元编码弱相关的数据特征。我们在三个数据集上说明了我们的发现:在机器学习中众所周知的Bars and Stripes和MNIST,以及在理论生物学中引入的所谓的Lattice Proteins,用于研究蛋白质中的序列到结构映射。
Universal representation by Boltzmann machines with Regularised Axons
ICFO - Institut de Ciències Fotòniques, The Barcelona Institute of Science and Technology(ICFO——光子科学研究所,巴塞罗那科学技术研究院);Adam Mickiewicz University(亚当·密茨凯维奇大学);Quside Technologies SL(Quside科技有限公司);Universitat Politècnica de València(瓦伦西亚理工大学);ICREA - Institució Catalana de Recerca i Estudis Avançats(ICREA——加泰罗尼亚研究与高级研究机构);University of Innsbruck(因斯布鲁克大学)