English
Related papers

Related papers: Wasserstein Convergence of Critically Damped Lange…

200 papers

The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting…

Machine Learning · Computer Science 2026-05-19 Anming Gu , Juno Kim

Stochastic Gradient Langevin Dynamics (SGLD) is a sampling scheme for Bayesian modeling adapted to large datasets and models. SGLD relies on the injection of Gaussian Noise at each step of a Stochastic Gradient Descent (SGD) update. In this…

Machine Learning · Computer Science 2018-06-11 Henri Palacci , Henry Hess

Discrete diffusion models have recently gained significant prominence in applications involving natural language and graph data. A key factor influencing their effectiveness is the efficiency of discretized samplers. Among these,…

Machine Learning · Computer Science 2025-11-03 Yuchen Liang , Yingbin Liang , Lifeng Lai , Ness Shroff

Deep generative models are universal tools for learning data distributions on high dimensional data spaces via a mapping to lower dimensional latent spaces. We provide a study of latent space geometries and extend and build upon previous…

Machine Learning · Computer Science 2019-02-07 Max F. Frenzel , Bogdan Teleaga , Asahi Ushio

Over the past few years, several approaches utilizing score-based diffusion have been proposed to sample from probability distributions, that is without having access to exact samples and relying solely on evaluations of unnormalized…

Machine Learning · Statistics 2025-04-15 Maxence Noble , Louis Grenioux , Marylou Gabrié , Alain Oliviero Durmus

Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed synaptic weights at convergence, in alignment with experimental observations in neuroscience.…

Machine Learning · Computer Science 2026-05-26 Nishanth Shetty , Madhava Prasath , Chandra Sekhar Seelamantula

Diffusion Models (DM) and Consistency Models (CM) are two types of popular generative models with good generation quality on various tasks. When training DM and CM, intermediate weight checkpoints are not fully utilized and only the last…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Enshu Liu , Junyi Zhu , Zinan Lin , Xuefei Ning , Shuaiqi Wang , Matthew B. Blaschko , Sergey Yekhanin , Shengen Yan , Guohao Dai , Huazhong Yang , Yu Wang

Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels). While Continuous Conditional Generative Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Xin Ding , Yongwei Wang , Kao Zhang , Z. Jane Wang

Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective. Compared with samplers with unbiased stationary…

Machine Learning · Computer Science 2024-03-12 Xunpeng Huang , Hanze Dong , Difan Zou , Tong Zhang

In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that this method can be formulated as a first order optimization algorithm of an objective functional defined on the Wasserstein space of order $2$. Using…

Computation · Statistics 2018-03-30 Alain Durmus , Szymon Majewski , Błażej Miasojedow

Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains. One adds gradually noise to data using a diffusion to transform the data distribution into a Gaussian distribution.…

Machine Learning · Computer Science 2023-08-21 Francisco Vargas , Will Grathwohl , Arnaud Doucet

Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or…

Diffusion models have quickly become some of the most popular and powerful generative models for high-dimensional data. The key insight that enabled their development was the realization that access to the score -- the gradient of the…

Machine Learning · Computer Science 2025-12-01 Zhenghan Fang , Mateo Díaz , Sam Buchanan , Jeremias Sulam

Approximate Bayesian inference estimates descriptors of an intractable target distribution - in essence, an optimization problem within a family of distributions. For example, Langevin dynamics (LD) extracts asymptotically exact samples…

Machine Learning · Statistics 2021-10-11 Zheyang Shen , Markus Heinonen , Samuel Kaski

Langevin Monte Carlo (LMC) and its stochastic gradient versions are powerful algorithms for sampling from complex high-dimensional distributions. To sample from a distribution with density $\pi(\theta)\propto \exp(-U(\theta)) $, LMC…

Computation · Statistics 2023-09-25 Sifan Liu

We propose a generalized Langevin dynamics (GLD) technique to construct non-Markovian particle-based coarse-grained models from fine-grained reference simulations and to efficiently integrate them. The proposed GLD model has the form of a…

Soft Condensed Matter · Physics 2018-11-16 Gerhard Jung , Martin Hanke , Friederike Schmid

In this paper, we consider the filtering problem for partially observed diffusions, which are regularly observed at discrete times. We are concerned with the case when one must resort to time-discretization of the diffusion process if the…

Numerical Analysis · Mathematics 2020-04-09 Marco Ballesio , Ajay Jasra , Erik von Schwerin , Raul Tempone

Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging. Standard approaches often rely on short-time…

Machine Learning · Statistics 2026-04-28 Ludovico T. Giorgini

Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution. A common approach involves simulating the time-reversal of an Ornstein-Uhlenbeck (OU) process initialized at…

Machine Learning · Statistics 2025-12-02 Valentin de Bortoli , Romuald Elie , Anna Kazeykina , Zhenjie Ren , Jiacheng Zhang

Acceleration is a celebrated cornerstone of convex optimization, enabling gradient-based algorithms to converge sublinearly in the condition number. A major open question is whether an analogous acceleration phenomenon is possible for…

Probability · Mathematics 2026-04-01 Jason M. Altschuler , Sinho Chewi , Matthew S. Zhang