English
Related papers

Related papers: Adapting to Mixing Time in Stochastic Optimization…

200 papers

Gradient-based temporal difference (GTD) algorithms are widely used in off-policy learning scenarios. Among them, the two time-scale TD with gradient correction (TDC) algorithm has been shown to have superior performance. In contrast to…

Machine Learning · Computer Science 2019-09-27 Tengyu Xu , Shaofeng Zou , Yingbin Liang

Decentralized stochastic gradient method emerges as a promising solution for solving large-scale machine learning problems. This paper studies the decentralized Markov chain gradient descent (DMGD) algorithm - a variant of the decentralized…

Optimization and Control · Mathematics 2021-04-14 Tao Sun , Dongsheng Li

Lifted Markov chains are Markov chains on graphs with added local "memory" and can be used to mix towards a target distribution faster than their memoryless counterparts. Upper and lower bounds on the achievable performance have been…

Optimization and Control · Mathematics 2017-05-24 Simon Apers , Francesco Ticozzi , Alain Sarlette

Statistical inference in evolutionary models with site-dependence is a long-standing challenge in phylogenetics and computational biology. We consider the problem of approximating marginal sequence likelihoods under dependent-site models of…

Computation · Statistics 2025-11-12 Joseph Mathews , Scott C. Schmidler

This paper studies some asymptotic properties of adaptive algorithms widely used in optimization and machine learning, and among them Adagrad and Rmsprop, which are involved in most of the blackbox deep learning algorithms. Our setup is the…

Machine Learning · Statistics 2020-12-15 Sébastien Gadat , Ioana Gavra

Multi-adaptive Galerkin methods are extensions of the standard continuous and discontinuous Galerkin methods for the numerical solution of initial value problems for ordinary or partial differential equations. In particular, the…

Numerical Analysis · Mathematics 2012-05-15 Johan Jansson , Anders Logg

We consider the problem of fitting variational posterior approximations using stochastic optimization methods. The performance of these approximations depends on (1) how well the variational family matches the true posterior…

This letter deals with the optimization problems of stochastic switching buffer networks, where the switching law is governed by Markov process. The dynamical buffer network is introduced, and its application in modeling the car-sharing…

Systems and Control · Electrical Eng. & Systems 2022-07-19 Chengyan Zhao , Kazunori Sakurama , Masaki Ogura

Temporal difference (TD) learning is a fundamental algorithm for estimating value functions in reinforcement learning. Recent finite-time analyses of TD with linear function approximation quantify its theoretical convergence rate. However,…

Machine Learning · Computer Science 2026-03-04 Yunxiang Li , Mark Schmidt , Reza Babanezhad , Sharan Vaswani

We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on…

Machine Learning · Computer Science 2020-06-23 Tom Zahavy , Alon Cohen , Haim Kaplan , Yishay Mansour

The problem of efficiently sampling from a set of (undirected, or directed) graphs with a given degree sequence has many applications. One approach to this problem uses a simple Markov chain, which we call the switch chain, to perform the…

Discrete Mathematics · Computer Science 2017-09-13 Catherine Greenhill , Matteo Sfragara

This paper considers a cross-layer optimization problem driven by multi-timescale stochastic exogenous processes in wireless communication networks. Due to the hierarchical information structure in a wireless network, a mixed timescale…

Systems and Control · Computer Science 2013-05-02 Junting Chen , Vincent K. N. Lau

Many problems in the physical sciences, machine learning, and statistical inference necessitate sampling from a high-dimensional, multi-modal probability distribution. Markov Chain Monte Carlo (MCMC) algorithms, the ubiquitous tool for this…

Data Analysis, Statistics and Probability · Physics 2022-05-12 Marylou Gabrié , Grant M. Rotskoff , Eric Vanden-Eijnden

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The…

Machine Learning · Computer Science 2019-04-08 Craig Wilson , Yuheng Bu , Venugopal Veeravalli

This paper deals with the problem of asymptotically optimal detection of changes in regime-switching stochastic models. We need to divide the whole obtained sample of data into several sub-samples with observations belonging to different…

Statistics Theory · Mathematics 2013-01-25 Boris Brodsky , Boris Darkhovsky

This paper proposes novel gradient-flow schemes that yield convergence to the optimal point of a convex optimization problem within a \textit{fixed} time from any given initial condition for unconstrained optimization, constrained…

Optimization and Control · Mathematics 2022-04-27 Kunal Garg , Dimitra Panagou

Continuous-time Markov chains are used to model stochastic systems where transitions can occur at irregular times, e.g., birth-death processes, chemical reaction networks, population dynamics, and gene regulatory networks. We develop a…

Machine Learning · Statistics 2022-12-13 Majerle Reeves , Harish S. Bhat

Motivated by broad applications in reinforcement learning and machine learning, this paper considers the popular stochastic gradient descent (SGD) when the gradients of the underlying objective function are sampled from Markov processes.…

Optimization and Control · Mathematics 2020-04-02 Thinh T. Doan , Lam M. Nguyen , Nhan H. Pham , Justin Romberg

We consider the problem of asynchronous stochastic optimization, where an optimization algorithm makes updates based on stale stochastic gradients of the objective that are subject to an arbitrary (possibly adversarial) sequence of delays.…

Optimization and Control · Mathematics 2025-06-23 Amit Attia , Ofir Gaash , Tomer Koren

We propose a stochastic trust-region method for unconstrained nonconvex optimization that incorporates stochastic variance-reduced gradients (SVRG) to accelerate convergence. Unlike classical trust-region methods, the proposed algorithm…

Optimization and Control · Mathematics 2026-01-22 Yuchen Fang , Xinshou Zheng , Javad Lavaei