English
Related papers

Related papers: Noise in the reverse process improves the approxim…

200 papers

This paper is devoted to order-one explicit approximations of random periodic solutions to multiplicative noise driven stochastic differential equations (SDEs) with non-globally Lipschitz coefficients. The existence of the random periodic…

Probability · Mathematics 2025-01-06 Yujia Guo , Xiaojie Wang , Yue Wu

Deterministic flow models, such as rectified flows, offer a general framework for learning a deterministic transport map between two distributions, realized as the vector field for an ordinary differential equation (ODE). However, they are…

Machine Learning · Computer Science 2024-10-04 Saurabh Singh , Ian Fischer

We introduce and analyze a novel class of inverse problems for stochastic dynamics: Given the ergodic invariant measure of a stochastic process governed by a nonlinear stochastic ordinary or partial differential equation (SODE or SPDE), we…

Probability · Mathematics 2026-03-03 Hongyu Liu , Zhihui Liu

Recently, neural ordinary differential equations (ODE) models trained with flow matching have achieved impressive performance on the zero-shot voice clone task. Nevertheless, postulating standard Gaussian noise as the initial distribution…

Sound · Computer Science 2025-03-28 Xuyuan Li , Zengqiang Shang , Hua Hua , Peiyang Shi , Chen Yang , Li Wang , Pengyuan Zhang

Stochastic Gradient Descent (SGD) is an out-of-equilibrium algorithm used extensively to train artificial neural networks. However very little is known on to what extent SGD is crucial for to the success of this technology and, in…

Machine Learning · Computer Science 2023-12-19 Persia Jana Kamali , Pierfrancesco Urbani

To obtain strong convergence rates of numerical schemes, an overwhelming majority of existing works impose a global monotonicity condition on coefficients of SDEs. Nevertheless, there are still many SDEs from applications that do not have…

Numerical Analysis · Mathematics 2025-04-03 Lei Dai , Xiaojie Wang

Although double-precision floating-point arithmetic currently dominates high-performance computing, there is increasing interest in smaller and simpler arithmetic types. The main reasons are potential improvements in energy efficiency and…

Data Structures and Algorithms · Computer Science 2020-01-23 Michael Hopkins , Mantas Mikaitis , Dave R. Lester , Steve Furber

We introduce a provably stable variant of neural ordinary differential equations (neural ODEs) whose trajectories evolve on an energy functional parametrised by a neural network. Stable neural flows provide an implicit guarantee on…

Machine Learning · Computer Science 2020-03-19 Stefano Massaroli , Michael Poli , Michelangelo Bin , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

Score-based generative models, which transform noise into data by learning to reverse a diffusion process, have become a cornerstone of modern generative AI. This paper contributes to establishing theoretical guarantees for the probability…

Machine Learning · Statistics 2025-02-03 Jiaqi Tang , Yuling Yan

In this paper we use neural networks to learn governing equations from data. Specifically we reconstruct the right-hand side of a system of ODEs $\dot{x}(t) = f(t, x(t))$ directly from observed uniformly time-sampled data using a neural…

Machine Learning · Computer Science 2021-08-18 Elisa Negrini , Giovanna Citti , Luca Capogna

We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support…

Statistics Theory · Mathematics 2025-06-25 Arthur Stéphanovitch

Diffusion-based generative models learn to iteratively transfer unstructured noise to a complex target distribution as opposed to Generative Adversarial Networks (GANs) or the decoder of Variational Autoencoders (VAEs) which produce samples…

Machine Learning · Computer Science 2022-10-26 Sarthak Mittal , Guillaume Lajoie , Stefan Bauer , Arash Mehrjou

Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some objectives, such as those found in complex-valued neural…

Machine Learning · Computer Science 2026-05-26 Natanael Alpay , Emeric Battaglia

Studying the properties of stochastic noise to optimize complex non-convex functions has been an active area of research in the field of machine learning. Prior work has shown that the noise of stochastic gradient descent improves…

Optimization and Control · Mathematics 2022-09-20 Aurelien Lucchi , Frank Proske , Antonio Orvieto , Francis Bach , Hans Kersting

While score-based generative models (SGMs) have achieved remarkable success in enormous image generation tasks, their mathematical foundations are still limited. In this paper, we analyze the approximation and generalization of SGMs in…

Machine Learning · Statistics 2024-02-26 Frank Cole , Yulong Lu

We introduce a new approach for designing numerical schemes for stochastic differential equations (SDEs). The approach, which we have called direction and norm decomposition method, proposes to approximate the required solution $X_t$ by…

Numerical Analysis · Mathematics 2017-02-21 C. M. Mora , H. A. Mardones , J. C. Jimenez , M. Selva , R. Biscay

Stochastic differential equations (SDEs) are well suited to modelling noisy and irregularly sampled time series found in finance, physics, and machine learning. Traditional approaches require costly numerical solvers to sample between…

Machine Learning · Computer Science 2025-10-30 Naoki Kiyohara , Edward Johns , Yingzhen Li

We propose a new Neural Galerkin Normalizing Flow framework to approximate the transition probability density function of a diffusion process by solving the corresponding Fokker-Planck equation with an atomic initial distribution,…

Machine Learning · Computer Science 2026-03-20 Riccardo Saporiti , Fabio Nobile

We discover restrained numerical instabilities in current training practices of deep networks with stochastic gradient descent (SGD), and its variants. We show numerical error (on the order of the smallest floating point bit and thus the…

Machine Learning · Computer Science 2024-06-13 Yuxin Sun , Dong Lao , Ganesh Sundaramoorthi , Anthony Yezzi

Probabilistic ordinary differential equation (ODE) solvers have been introduced over the past decade as uncertainty-aware numerical integrators. They typically proceed by assuming a functional prior to the ODE solution, which is then…

Numerical Analysis · Mathematics 2025-03-25 Yvann Le Fay , Simo Särkkä , Adrien Corenflos