English
Related papers

Related papers: A closed-measure approach to stochastic approximat…

200 papers

We first propose the concept of Stepanov-like weighted pseudo-almost automorphic on time-space scales and we apply this type of oscillation to high-order BAM neural networks with mixed delays. Then, we study the existence and exponential…

Dynamical Systems · Mathematics 2018-03-15 Adnène Arbi

We study the convergence of random function iterations for finding an invariant measure of the corresponding Markov operator. We call the problem of finding such an invariant measure the stochastic fixed point problem. This generalizes…

Optimization and Control · Mathematics 2024-04-16 Neal Hermer , D. Russell Luke , Anja Sturm

Point source localisation is generally modelled as a Lasso-type problem on measures. However, optimisation methods in non-Hilbert spaces, such as the space of Radon measures, are much less developed than in Hilbert spaces. Most numerical…

Optimization and Control · Mathematics 2024-02-14 Tuomo Valkonen

We consider the Cauchy problem for a semilinear stochastic differential inclusion in a Hilbert space. The linear operator generates a strongly continuous semigroup and the nonlinear term is multivalued and satisfies a condition which is…

Probability · Mathematics 2007-05-23 Adam Jakubowski , Mikhail Kamenskii , Paul Raynaud De Fitte

Stein's method is used to approximate sums of discrete and locally dependent random variables by a centered and symmetric Binomial distribution. Under appropriate smoothness properties of the summands, the same order of accuracy as in the…

Probability · Mathematics 2007-05-23 Adrian Röllin

This work provides a novel convergence analysis for stochastic optimization in terms of stopping times, addressing the practical reality that algorithms are often terminated adaptively based on observed progress. Unlike prior approaches,…

Optimization and Control · Mathematics 2025-07-17 Yasong Feng , Yifan Jiang , Tianyu Wang , Zhiliang Ying

This work explores the use of a forward-backward martingale method together with a decoupling argument and entropic estimates between the conditional and averaged measures to prove a strong averaging principle for stochastic differential…

Probability · Mathematics 2017-09-18 Bob Pepin

In this paper, we study the almost sure boundedness and the convergence of the stochastic approximation (SA) algorithm. At present, most available convergence proofs are based on the ODE method, and the almost sure boundedness of the…

Machine Learning · Statistics 2023-01-10 M. Vidyasagar

Gradient optimization algorithms using epochs, that is those based on stochastic gradient descent without replacement (SGDo), are predominantly used to train machine learning models in practice. However, the mathematical theory of SGDo and…

Machine Learning · Computer Science 2025-12-05 Stefan Perko

We consider an incremental approximation method for solving variational problems in infinite-dimensional Hilbert spaces, where in each step a randomly and independently selected subproblem from an infinite collection of subproblems is…

Numerical Analysis · Mathematics 2018-03-06 Michael Griebel , Peter Oswald

We propose some new mixed finite element methods for the time dependent stochastic Stokes equations with multiplicative noise, which use the Helmholtz decomposition of the driving multiplicative noise. It is known [16] that the pressure…

Numerical Analysis · Mathematics 2020-06-09 Xiaobing Feng , Andreas Prohl , Liet Vo

We present a new method for sampling rare and large fluctuations in a non-equilibrium system governed by a stochastic partial differential equation (SPDE) with additive forcing. To this end, we deploy the so-called instanton formalism that…

Computational Physics · Physics 2019-06-26 Lasse Ebener , Georgios Margazoglou , Jan Friedrich , Luca Biferale , Rainer Grauer

The Robbins-Monro algorithm is a recursive, simulation-based stochastic procedure to approximate the zeros of a function that can be written as an expectation. It is known that under some technical assumptions, Gaussian limit distributions…

Probability · Mathematics 2025-10-22 Valentin Konakov , Enno Mammen , Lorick Huang

Many matching, tracking, sorting, and ranking problems require probabilistic reasoning about possible permutations, a set that grows factorially with dimension. Combinatorial optimization algorithms may enable efficient point estimation,…

Machine Learning · Statistics 2017-10-27 Scott W. Linderman , Gonzalo E. Mena , Hal Cooper , Liam Paninski , John P. Cunningham

We prove the almost sure weak convergence of a stochastic proximal point method for minimizing a convex integral function in the general nonlinear context of complete geodesic metric spaces of nonpositive curvature (so-called Hadamard…

Optimization and Control · Mathematics 2026-05-21 Nicholas Pischke

This paper is concerned with the proof of existence and numerical approximation of large-data global-in-time Young measure solutions to initial-boundary-value problems for multidimensional nonlinear parabolic systems of forward-backward…

Numerical Analysis · Mathematics 2019-02-28 Miles Caddick , Endre Süli

This work proposes an implementable proximal-type method for a broad class of optimization problems involving nonsmooth and nonconvex objective and constraint functions. In contrast to existing methods that rely on an ad hoc model…

Optimization and Control · Mathematics 2024-09-26 Gregorio M. Sempere , Welington de Oliveira , Johannes O. Royset

This paper addresses the challenging numerical simulation of nonlinear hybrid stochastic functional differential equations with infinite delays. We first propose an explicit scheme using space and time truncation, requiring only finite…

Numerical Analysis · Mathematics 2025-12-23 Guozhen Li , Xiaoyue Li , Xuerong Mao

Many machine learning and optimization algorithms are built upon the framework of stochastic approximation (SA), for which the selection of step-size (or learning rate) $\{\alpha_n\}$ is crucial for success. An essential condition for…

Statistics Theory · Mathematics 2025-08-05 Caio Kalil Lauand , Sean Meyn

In this manuscript, we propose a general proximal quasi-Newton method tailored for nonconvex and nonsmooth optimization problems, where we do not require the sequence of the variable metric (or Hessian approximation) to be uniformly bounded…

Optimization and Control · Mathematics 2025-07-28 Xiaoxi Jia