English
Related papers

Related papers: Emergence of AdS geometry in the simulated temperi…

200 papers

With the recent proliferation of large-scale learning problems,there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its variants. However,…

Machine Learning · Computer Science 2015-12-07 Ruiliang Zhang , Shuai Zheng , James T. Kwok

Context. High-resolution numerical methods have been developed for nonlinear, discontinuous problems as they appear in simulations of astrophysical objects. One of the strategies applied is the concept of artificial viscosity. Aims.…

Instrumentation and Methods for Astrophysics · Physics 2013-06-19 Harald Höller , Antti Koskela , Ernst Dorfi , Werner Benger

Stochastic gradient descent (SGD) has been a go-to algorithm for nonconvex stochastic optimization problems arising in machine learning. Its theory however often requires a strong framework to guarantee convergence properties. We hereby…

Optimization and Control · Mathematics 2025-03-11 Azar Louzi

One of the most widely used methods for solving large-scale stochastic optimization problems is distributed asynchronous stochastic gradient descent (DASGD), a family of algorithms that result from parallelizing stochastic gradient descent…

Optimization and Control · Mathematics 2021-07-08 Zhengyuan Zhou , Panayotis Mertikopoulos , Nicholas Bambos , Peter W. Glynn , Yinyu Ye

Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how…

Machine Learning · Computer Science 2026-03-25 Shengping Xie , Zekun Wu , Quan Chen , Kaixu Tang

Comparing metric measure spaces (i.e. a metric space endowed with aprobability distribution) is at the heart of many machine learning problems. The most popular distance between such metric measure spaces is theGromov-Wasserstein (GW)…

Optimization and Control · Mathematics 2023-01-18 Thibault Séjourné , François-Xavier Vialard , Gabriel Peyré

In this paper we consider convergence rate problems for stochastic strongly-convex optimization in the non-Euclidean sense with a constraint set over a time-varying multi-agent network. We propose two efficient non-Euclidean stochastic…

Optimization and Control · Mathematics 2018-08-23 Deming Yuan , Yiguang Hong , Daniel W. C. Ho , Guoping Jiang

Computing smoothing distributions, the distributions of one or more states conditional on past, present, and future observations is a recurring problem when operating on general hidden Markov models. The aim of this paper is to provide a…

Probability · Mathematics 2012-02-15 Randal Douc , Aurélien Garivier , Eric Moulines , Jimmy Olsson

Parallel tempering (PT) methods are a popular class of Markov chain Monte Carlo schemes used to sample complex high-dimensional probability distributions. They rely on a collection of $N$ interacting auxiliary chains targeting tempered…

Computation · Statistics 2021-07-28 Saifuddin Syed , Alexandre Bouchard-Côté , George Deligiannidis , Arnaud Doucet

The prohibitive cost of performing Uncertainty Quantification (UQ) tasks with a very large number of input parameters can be addressed, if the response exhibits some special structure that can be discovered and exploited. Several physical…

Computational Physics · Physics 2016-02-16 Ilias Bilionis , Rohit Tripathy , Marcial Gonzalez

The pseudo-marginal algorithm is a variant of the Metropolis--Hastings algorithm which samples asymptotically from a probability distribution when it is only possible to estimate unbiasedly an unnormalized version of its density.…

Computation · Statistics 2019-12-04 Sebastian M. Schmon , George Deligiannidis , Arnaud Doucet , Michael K. Pitt

We consider the problem of model selection in Gaussian Markov fields in the sample deficient scenario. In many practically important cases, the underlying networks are embedded into Euclidean spaces. Using the natural geometric structure,…

Machine Learning · Statistics 2018-10-31 Ilya Soloveychik , Vahid Tarokh

Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled by a so-called…

Optimization and Control · Mathematics 2025-06-30 Yufeng Yang , Yi Zhou , Zhaosong Lu

We propose an algorithm for optimizations in which the gradients contain stochastic noise. This arises, for example, in structural optimizations when computations of forces and stresses rely on methods involving Monte Carlo sampling, such…

Materials Science · Physics 2022-11-30 Siyuan Chen , Shiwei Zhang

Importance sampling is a Monte Carlo method that introduces a proposal distribution to sample the space according to the target distribution. Yet calibration of the proposal distribution is essential to achieving efficiency, thus the resort…

Computation · Statistics 2022-06-17 Grégoire Aufort , Pierre Pudlo , Denis Burgarella

Metastability is a formidable challenge to Markov chain Monte Carlo methods. In this paper we present methods for algorithm design to meet this challenge. The design problem we consider is temperature selection for the infinite swapping…

Probability · Mathematics 2020-11-12 Paul Dupuis , Guo-Jhen Wu

In the field of optimal transport, two prominent subfields face each other: (i) unregularized optimal transport, "\`a-la-Kantorovich", which leads to extremely sparse plans but with algorithms that scale poorly, and (ii)…

Machine Learning · Computer Science 2024-02-19 Ehsan Amid , Frank Nielsen , Richard Nock , Manfred K. Warmuth

The tuning of stochastic gradient algorithms (SGAs) for optimization and sampling is often based on heuristics and trial-and-error rather than generalizable theory. We address this theory--practice gap by characterizing the large-sample…

Computation · Statistics 2023-07-21 Jeffrey Negrea , Jun Yang , Haoyue Feng , Daniel M. Roy , Jonathan H. Huggins

We generalize stochastic subgradient descent methods to situations in which we do not receive independent samples from the distribution over which we optimize, but instead receive samples that are coupled over time. We show that as long as…

Optimization and Control · Mathematics 2012-08-02 John C. Duchi , Alekh Agarwal , Mikael Johansson , Michael I. Jordan

Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal transport have been…

Optimization and Control · Mathematics 2023-01-18 Thibault Séjourné , Jean Feydy , François-Xavier Vialard , Alain Trouvé , Gabriel Peyré
‹ Prev 1 8 9 10 Next ›