English
Related papers

Related papers: Stable generative modeling using Schr\"odinger bri…

200 papers

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

Statistics Theory · Mathematics 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

Generative models using neural network have opened a door to large-scale studies for various application domains, especially for studies that suffer from lack of real samples to obtain statistically robust inference. Typically, these…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Seong Jae Hwang , Zirui Tao , Won Hwa Kim , Vikas Singh

In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form…

Machine Learning · Computer Science 2025-02-28 Saeid Naderiparizi , Xiaoxuan Liang , Berend Zwartsenberg , Frank Wood

Motivated by applications in trajectory inference and particle tracking, we introduce Smooth Schr\"odinger Bridges. Our proposal generalizes prior work by allowing the reference process in the Schr\"odinger Bridge problem to be a smooth…

Machine Learning · Statistics 2025-03-04 Wanli Hong , Yuliang Shi , Jonathan Niles-Weed

In a recent article, Krapivsky and Redner (J. Stat. Mech. 093208 (2018)) established that the distribution of the first hitting times for a diffusing particle subject to hitting an absorber is independent of the direction of the external…

Statistical Mechanics · Physics 2020-01-29 Coline Larmier , Alain Mazzolo , Andrea Zoia

Erwin Schroedinger posed, and to a large extent solved in 1931/32 the problem of finding the most likely random evolution between two continuous probability distributions. This article considers this problem in the case when only samples of…

Optimization and Control · Mathematics 2018-06-07 Michele Pavon , Esteban G Tabak , Giulio Trigila

Generative robotic motion planning requires not only the synthesis of smooth and collision-free trajectories but also feasibility across diverse tasks and dynamic constraints. Prior planning methods, both traditional and generative, often…

Robotics · Computer Science 2025-12-02 Khang Nguyen , Minh Nhat Vu

Large-size populations consisting of a continuum of identical and non-cooperative agents with stochastic dynamics are useful in modeling various biological and engineered systems. This paper addresses the stochastic control problem of…

Optimization and Control · Mathematics 2020-10-02 Kaivalya Bakshi , David D. Fan , Evangelos A. Theodorou

We propose a novel stochastic method to exactly generate Brownian paths conditioned to start at an initial point and end at a given final point during a fixed time $t_{f}$. These paths are weighted with a probability given by the overdamped…

Statistical Mechanics · Physics 2015-05-14 Satya N. Majumdar , Henri Orland

Transporting between arbitrary distributions is a fundamental goal in generative modeling. Recently proposed diffusion bridge models provide a potential solution, but they rely on a joint distribution that is difficult to obtain in…

Machine Learning · Computer Science 2025-03-03 Jun Hyeong Kim , Seonghwan Kim , Seokhyun Moon , Hyeongwoo Kim , Jeheon Woo , Woo Youn Kim

This work studies the Schr\"odinger bridge problem for the kinematic equation on a compact connected Lie group. The objective is to steer a controlled diffusion between given initial and terminal densities supported over the Lie group while…

Optimization and Control · Mathematics 2026-03-23 Hamza Mahmood , Abhishek Halder , Adeel Akhtar

We propose a hybrid generative model for efficient sampling of high-dimensional, multimodal probability distributions for Bayesian inference. Traditional Monte Carlo methods, such as the Metropolis-Hastings and Langevin Monte Carlo sampling…

Machine Learning · Statistics 2025-05-14 Hoang Tran , Zezhong Zhang , Feng Bao , Dan Lu , Guannan Zhang

Score-based generative models have demonstrated significant practical success in data-generating tasks. The models establish a diffusion process that perturbs the ground truth data to Gaussian noise and then learn the reverse process to…

Machine Learning · Computer Science 2024-05-24 Ziqing Wen , Xiaoge Deng , Ping Luo , Tao Sun , Dongsheng Li

A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo and Vanden-Eijnden (2023), enabling the use of a broad class of continuous-time stochastic…

Machine Learning · Computer Science 2025-10-10 Michael S. Albergo , Nicholas M. Boffi , Eric Vanden-Eijnden

We consider numerical methods for thermodynamic sampling, i.e. computing sequences of points distributed according to the Gibbs-Boltzmann distribution, using Langevin dynamics and overdamped Langevin dynamics (Brownian dynamics). A wide…

Statistical Mechanics · Physics 2015-01-13 Benedict Leimkuhler , Charles Matthews , Gabriel Stoltz

We derive a novel generative model from iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we can formulate the sampling process in the language of Bayesian probability. Our model uses a…

Machine Learning · Computer Science 2026-01-28 Marten Lienen , Marcel Kollovieh , Stephan Günnemann

Sampling conditional distributions is a fundamental task for Bayesian inference and density estimation. Generative models, such as normalizing flows and generative adversarial networks, characterize conditional distributions by learning a…

We propose a deep generative approach to sampling from a conditional distribution based on a unified formulation of conditional distribution and generalized nonparametric regression function using the noise-outsourcing lemma. The proposed…

Statistics Theory · Mathematics 2021-10-22 Xingyu Zhou , Yuling Jiao , Jin Liu , Jian Huang

Use energy-based model for bridge-type innovation. The loss function is explained by the game theory, the logic is clear and the formula is simple and clear. Thus avoid the use of maximum likelihood estimation to explain the loss function…

Machine Learning · Computer Science 2024-02-01 Hongjun Zhang

Scientists often want to make predictions beyond the observed time horizon of "snapshot" data following latent stochastic dynamics. For example, in time course single-cell mRNA profiling, scientists have access to cellular transcriptional…

Machine Learning · Statistics 2025-05-23 Renato Berlinghieri , Yunyi Shen , Jialong Jiang , Tamara Broderick
‹ Prev 1 4 5 6 7 8 10 Next ›