English
Related papers

Related papers: String Method for Generalized Gradient Flows: Comp…

200 papers

Understanding the geometry of learned distributions is fundamental to improving and interpreting diffusion models, yet systematic tools for exploring their landscape remain limited. Standard latent-space interpolations fail to respect the…

Machine Learning · Statistics 2026-02-26 Elio Moreau , Florentin Coeurdoux , Grégoire Ferre , Eric Vanden-Eijnden

We study the implicit regularization of mini-batch stochastic gradient descent, when applied to the fundamental problem of least squares regression. We leverage a continuous-time stochastic differential equation having the same moments as…

Machine Learning · Statistics 2020-06-23 Alnur Ali , Edgar Dobriban , Ryan J. Tibshirani

Multiplicative cascades have been introduced in turbulence to generate random or deterministic fields having intermittent values and long-range power-law correlations. Generally this is done using discrete construction rules leading to…

Statistical Mechanics · Physics 2007-05-23 Francois G. Schmitt

Sampling a target probability distribution with an unknown normalization constant is a fundamental challenge in computational science and engineering. Recent work shows that algorithms derived by considering gradient flows in the space of…

Machine Learning · Statistics 2024-03-12 Yifan Chen , Daniel Zhengyu Huang , Jiaoyang Huang , Sebastian Reich , Andrew M Stuart

Stochastic gradient methods are scalable for solving large-scale optimization problems that involve empirical expectations of loss functions. Existing results mainly apply to optimization problems where the objectives are one- or two-level…

Optimization and Control · Mathematics 2018-01-15 Shuoguang Yang , Mengdi Wang , Ethan X. Fang

This thesis develops exact analytical tools to study strongly correlated stochastic systems, with a focus on extreme value statistics, gap statistics, and full counting statistics in multi-particle processes. A central contribution is the…

Statistical Mechanics · Physics 2025-08-19 Marco Biroli

Turbulent cascades characterize the transfer of energy injected by a random force at large scales towards the small scales. In hydrodynamic turbulence, when the Reynolds number is large, the velocity field of the fluid becomes irregular and…

Mathematical Physics · Physics 2023-12-05 Gabriel B. Apolinário , Geoffrey Beck , Laurent Chevillard , Isabelle Gallagher , Ricardo Grande

We consider the stochastic gradient method with random reshuffling ($\mathsf{RR}$) for tackling smooth nonconvex optimization problems. $\mathsf{RR}$ finds broad applications in practice, notably in training neural networks. In this work,…

Optimization and Control · Mathematics 2026-04-17 Hengxu Yu , Xiao Li

Random Reshuffling (RR) is an algorithm for minimizing finite-sum functions that utilizes iterative gradient descent steps in conjunction with data reshuffling. Often contrasted with its sibling Stochastic Gradient Descent (SGD), RR is…

Optimization and Control · Mathematics 2021-04-06 Konstantin Mishchenko , Ahmed Khaled , Peter Richtárik

Sampling a probability distribution with an unknown normalization constant is a fundamental problem in computational science and engineering. This task may be cast as an optimization problem over all probability measures, and an initial…

Machine Learning · Statistics 2024-09-12 Yifan Chen , Daniel Zhengyu Huang , Jiaoyang Huang , Sebastian Reich , Andrew M. Stuart

In this paper, we study a simple hydrodynamical model showing abrupt flow reversals at random times. For a suitable range of parameters, we show that the dynamics of flow reversal is accurately described by stochastic differential…

Chaotic Dynamics · Physics 2009-11-10 Roberto Benzi

Modern machine learning systems represent their computations as dataflow graphs. The increasingly complex neural network architectures crave for more powerful yet efficient programming abstractions. In this paper we propose an efficient…

Programming Languages · Computer Science 2024-10-29 Kelly Kostopoulou , Angelos Charalambidis , Panos Rondogiannis

Transition path sampling is a method for estimating the rates of rare events in molecular systems based on the gradual transformation of a path distribution containing a small fraction of reactive trajectories into a biased distribution in…

Statistical Mechanics · Physics 2015-10-28 Pierre Terrier , Mihai-Cosmin Marinica , Manuel Athènes

This paper is concerned with classes of models of stochastic reaction dynamics with time-scales separation. We demonstrate that the existence of the time-scale separation naturally leads to the application of the averaging principle and…

Computational Physics · Physics 2007-05-23 Sergey Plyasunov

Random geometric graphs (RGG) can be formalized as hidden-variables models where the hidden variables are the coordinates of the nodes. Here we develop a general approach to extract the typical configurations of a generic hidden-variables…

Disordered Systems and Neural Networks · Physics 2015-04-28 Massimo Ostilli , Ginestra Bianconi

The Cartesian reverse derivative is a categorical generalization of reverse-mode automatic differentiation. We use this operator to generalize several optimization algorithms, including a straightforward generalization of gradient descent…

Optimization and Control · Mathematics 2021-09-22 Dan Shiebler

We review two recently developed efficient methods for calculating rate constants of processes dominated by rare events in high-dimensional complex systems. The first is transition interface sampling (TIS), based on the measurement of…

Statistical Mechanics · Physics 2009-11-10 Titus S. van Erp , Peter G. Bolhuis

We present a stochastic method for reconstructing missing spatial and velocity data along the trajectories of small objects passively advected by turbulent flows with a wide range of temporal or spatial scales, such as small balloons in the…

Fluid Dynamics · Physics 2024-11-14 Tianyi Li , Luca Biferale , Fabio Bonaccorso , Michele Buzzicotti , Luca Centurioni

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine Learning · Computer Science 2025-12-05 Dravyansh Sharma

We present well-balanced, high-order, semi-discrete numerical schemes for one-dimensional blood flow models with discontinuous mechanical properties and algebraic source terms representing friction and gravity. While discontinuities in…

Numerical Analysis · Mathematics 2025-08-29 Ernesto Pimentel-García , Lucas O. Müller , Carlos Parés