English
Related papers

Related papers: One-Step Sampler for Boltzmann Distributions via D…

200 papers

Stochastic Gradient Descent (SGD) is a popular optimization method which has been applied to many important machine learning tasks such as Support Vector Machines and Deep Neural Networks. In order to parallelize SGD, minibatch training is…

Machine Learning · Statistics 2014-05-14 Peilin Zhao , Tong Zhang

We propose the characteristic generator, a novel one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models. Our model is driven by…

Machine Learning · Computer Science 2025-12-29 Zhao Ding , Chenguang Duan , Yuling Jiao , Ruoxuan Li , Jerry Zhijian Yang , Pingwen Zhang

We study the problem of learning in the presence of a drifting target concept. Specifically, we provide bounds on the error rate at a given time, given a learner with access to a history of independent samples labeled according to a target…

Machine Learning · Computer Science 2015-05-21 Steve Hanneke , Varun Kanade , Liu Yang

Normalizing flows are a popular class of models for approximating probability distributions. However, their invertible nature limits their ability to model target distributions whose support have a complex topological structure, such as…

Machine Learning · Statistics 2022-02-25 Vincent Stimper , Bernhard Schölkopf , José Miguel Hernández-Lobato

Optimal transport is widely used to learn distributions, enforce distributional constraints, and model uncertainty. In applications, transport losses are often computed from samples through tractable representations, such as one-dimensional…

Optimization and Control · Mathematics 2026-05-28 Tam Le

We investigate the problem of sampling from posterior distributions with intractable normalizing constants in Bayesian inference. Our solution is a new generative modeling approach based on optimal transport (OT) that learns a deterministic…

Computation · Statistics 2026-03-03 Ke Li , Wei Han , Yuexi Wang , Yun Yang

We prove that a denoising diffusion sampler equipped with a sequential bias across the batch dimension is exactly an Euler-Maruyama integrator for overdamped Langevin dynamics. Each reverse denoising step, with its associated spring…

Machine Learning · Computer Science 2025-12-01 Justin Diamond , Markus Lill

In this article, we focus on the sampling of the configurational Gibbs-Boltzmann distribution, that is, the calculation of averages of functions of the position coordinates of a molecular $N$-body system modelled at constant temperature. We…

Numerical Analysis · Mathematics 2025-04-30 Benedict Leimkuhler , Charles Matthews

In recent years, diffusion models trained on equilibrium molecular distributions have proven effective for sampling biomolecules. Beyond direct sampling, the score of such a model can also be used to derive the forces that act on molecular…

Machine Learning · Computer Science 2026-01-15 Michael Plainer , Hao Wu , Leon Klein , Stephan Günnemann , Frank Noé

Diffusion models generate samples by estimating the score function of the target distribution at various noise levels. The model is trained using samples drawn from the target distribution by progressively adding noise. Previous sample…

Machine Learning · Computer Science 2025-10-28 Syamantak Kumar , Dheeraj Nagaraj , Purnamrita Sarkar

We introduce a novel unit-time ordinary differential equation (ODE) flow called the preconditioned F\"{o}llmer flow, which efficiently transforms a Gaussian measure into a desired target measure at time 1. To discretize the flow, we apply…

Methodology · Statistics 2023-11-08 Zhao Ding , Yuling Jiao , Xiliang Lu , Zhijian Yang , Cheng Yuan

We consider the problem of optimising the expected value of a loss functional over a nonlinear model class of functions, assuming that we have only access to realisations of the gradient of the loss. This is a classical task in statistics,…

Optimization and Control · Mathematics 2026-02-02 Robert Gruhlke , Anthony Nouy , Philipp Trunschke

We present a concise derivation of the Boltzmann form for single-particle energy distributions in classical many-body Hamiltonian systems. The derivation relies on two physical facts: coarse-graining-scale invariance of the empirical…

Statistical Mechanics · Physics 2026-05-26 Weicheng Fu , Yisen Wang , Yong Zhang , Hong Zhao

One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillation-free methods, MeanFlow training is notoriously unstable, with non-decreasing loss and…

Machine Learning · Computer Science 2026-05-12 Juanwu Lu , Ziran Wang

Imperfect score-matching leads to a shift between the training and the sampling distribution of diffusion models. Due to the recursive nature of the generation process, errors in previous steps yield sampling iterates that drift away from…

Machine Learning · Computer Science 2023-02-20 Giannis Daras , Yuval Dagan , Alexandros G. Dimakis , Constantinos Daskalakis

The molecular dynamics lattice gas method maps a molecular dynamics simulation onto a lattice gas using a coarse-graining procedure. This is a novel fundamental approach to derive the lattice Boltzmann method by taking a Boltzmann average…

Computational Physics · Physics 2021-10-04 Aleksandra Pachalieva , Alexander J. Wagner

The sampling of Boltzmann distributions by stochastic Markov processes, can be strongly limited by the crossing time of high (free) energy barriers. As a result, the system may stay trapped in metastable states, and the relaxation time to…

Statistical Mechanics · Physics 2015-05-13 Henri Orland

In a two-stage cluster sampling procedure, $n$ random populations are drawn independently from independent populations and a sub-sample of observations is taken in each of them. The estimator of the general mean of the observed variables is…

Statistics Theory · Mathematics 2009-09-29 Odile Pons

We extend nonparametric regression smoothing splines to a context where there is endogeneity and instrumental variables are available. Unlike popular existing estimators, the resulting estimator is one-step and relies on a unique…

Econometrics · Economics 2024-12-10 Jad Beyhum , Elia Lapenta , Pascal Lavergne

Generative models have shown immense potential for wireless communication by learning complex channel data distributions. However, the iterative denoising process associated with these models imposes a significant challenge in…

Information Theory · Computer Science 2026-01-26 Zehua Jiang , Fenghao Zhu , Siming Jiang , Chongwen Huang , Zhaohui Yang , Richeng Jin , Zhaoyang Zhang , Merouane Debbah
‹ Prev 1 3 4 5 6 7 10 Next ›