English
Related papers

Related papers: Concentration bounds for temporal difference learn…

200 papers

We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors. We develop stochastic quadratic constraints to formulate a small linear matrix…

Optimization and Control · Mathematics 2020-03-31 Bin Hu , Peter Seiler , Laurent Lessard

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

Machine Learning · Computer Science 2025-04-21 Han-Dong Lim , Donghwan Lee

Stochastic iterative algorithms, including stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD), are widely utilized for optimization and sampling in large-scale and high-dimensional problems in machine…

Machine Learning · Statistics 2025-01-22 Xiaoyu Wang , Mikolaj J. Kasprzak , Jeffrey Negrea , Solesne Bourguin , Jonathan H. Huggins

Stochastic gradients have been widely integrated into Langevin-based methods to improve their scalability and efficiency in solving large-scale sampling problems. However, the proximal sampler, which exhibits much faster convergence than…

Machine Learning · Statistics 2024-05-28 Xunpeng Huang , Difan Zou , Yi-An Ma , Hanze Dong , Tong Zhang

The recent emergence of reinforcement learning has created a demand for robust statistical inference methods for the parameter estimates computed using these algorithms. Existing methods for statistical inference in online learning are…

Machine Learning · Statistics 2022-06-29 Pratik Ramprasad , Yuantong Li , Zhuoran Yang , Zhaoran Wang , Will Wei Sun , Guang Cheng

Stochastic gradient descent (SGD) algorithm and its variations have been effectively used to optimize neural network models. However, with the rapid growth of big data and deep learning, SGD is no longer the most suitable choice due to its…

Machine Learning · Computer Science 2024-02-13 Anuraganand Sharma

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time…

Machine Learning · Computer Science 2016-03-16 Guillaume Bouchard , Théo Trouillon , Julien Perez , Adrien Gaidon

We study the complexity of smoothed agnostic learning, recently introduced by~\cite{CKKMS24}, in which the learner competes with the best classifier in a target class under slight Gaussian perturbations of the inputs. Specifically, we focus…

Machine Learning · Computer Science 2026-02-25 Ilias Diakonikolas , Daniel M. Kane

Two timescale stochastic approximation (SA) has been widely used in value-based reinforcement learning algorithms. In the policy evaluation setting, it can model the linear and nonlinear temporal difference learning with gradient correction…

Machine Learning · Computer Science 2020-11-11 Tengyu Xu , Yingbin Liang

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides…

Machine Learning · Computer Science 2025-06-19 Alexandru Meterez , Depen Morwani , Costin-Andrei Oncescu , Jingfeng Wu , Cengiz Pehlevan , Sham Kakade

Stochastic gradient descent (SGD) is the optimization algorithm of choice in many machine learning applications such as regularized empirical risk minimization and training deep neural networks. The classical convergence analysis of SGD is…

Optimization and Control · Mathematics 2018-07-10 Lam M. Nguyen , Phuong Ha Nguyen , Marten van Dijk , Peter Richtárik , Katya Scheinberg , Martin Takáč

In this paper, we introduce a new approach to proving the convergence of the Stochastic Approximation (SA) and the Stochastic Gradient Descent (SGD) algorithms. The new approach is based on a concept called GSLLN (Generalized Strong Law of…

Optimization and Control · Mathematics 2025-11-11 Rajeeva Laxman Karandikar , Bhamidi Visweswara Rao , Mathukumalli Vidyasagar

SGD (Stochastic Gradient Descent) is a popular algorithm for large scale optimization problems due to its low iterative cost. However, SGD can not achieve linear convergence rate as FGD (Full Gradient Descent) because of the inherent…

Machine Learning · Computer Science 2017-12-05 Aixiang Chen , Bingchuan Chen , Xiaolong Chai , Rui Bian , Hengguang Li

SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automated stepsize that works well across a wide range of convex…

Optimization and Control · Mathematics 2024-02-22 Zachary Frangella , Pratik Rathore , Shipu Zhao , Madeleine Udell

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 introduce a clipping strategy for Stochastic Gradient Descent (SGD) which uses quantiles of the gradient norm as clipping thresholds. We prove that this new strategy provides a robust and efficient optimization algorithm for smooth…

Machine Learning · Statistics 2024-10-15 Ibrahim Merad , Stéphane Gaïffas

Stochastic approximation (SA) is a powerful class of iterative algorithms for nonlinear root-finding that can be used for minimizing a loss function, $L(\boldsymbol{\theta})$, with respect to a parameter vector $\boldsymbol{\theta}$, when…

Optimization and Control · Mathematics 2017-07-24 Karla Hernández Cuevas

We develop a new randomized iterative algorithm---stochastic dual ascent (SDA)---for finding the projection of a given vector onto the solution space of a linear system. The method is dual in nature: with the dual being a non-strongly…

Numerical Analysis · Mathematics 2016-01-29 Robert Mansel Gower , Peter Richtarik

Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as GTD(0), GTD2, and TDC. Here, we provide convergence rate…

Machine Learning · Computer Science 2019-12-05 Gal Dalal , Balazs Szorenyi , Gugan Thoppe

Spatiotemporal data analysis is pivotal across various domains, such as transportation, meteorology, and healthcare. The data collected in real-world scenarios are often incomplete due to device malfunctions and network errors.…

Machine Learning · Computer Science 2024-03-25 Yakun Chen , Kaize Shi , Zhangkai Wu , Juan Chen , Xianzhi Wang , Julian McAuley , Guandong Xu , Shui Yu