English
Related papers

Related papers: Closing the gap between SVRG and TD-SVRG with Grad…

200 papers

Value function approximation is a crucial module for policy evaluation in reinforcement learning when the state space is large or continuous. The present paper takes a generative perspective on policy evaluation via temporal-difference (TD)…

Machine Learning · Statistics 2021-12-03 Qin Lu , Georgios B. Giannakis

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

Machine Learning · Computer Science 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman

TD(0) is one of the most commonly used algorithms in reinforcement learning. Despite this, there is no existing finite sample analysis for TD(0) with function approximation, even for the linear case. Our work is the first to provide such…

Artificial Intelligence · Computer Science 2017-12-12 Gal Dalal , Balázs Szörényi , Gugan Thoppe , Shie Mannor

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

The learning rate is perhaps the single most important parameter in the training of neural networks and, more broadly, in stochastic (nonconvex) optimization. Accordingly, there are numerous effective, but poorly understood, techniques for…

Machine Learning · Computer Science 2020-04-16 Bin Shi , Weijie J. Su , Michael I. Jordan

Relative temporal-difference (TD) learning was introduced to mitigate the slow convergence of TD methods when the discount factor approaches one by subtracting a baseline from the temporal-difference update. While this idea has been studied…

Machine Learning · Computer Science 2026-04-08 Masoud S. Sakha , Rushikesh Kamalapurkar , Sean Meyn

In a broad class of reinforcement learning applications, stochastic rewards have heavy-tailed distributions, which lead to infinite second-order moments for stochastic (semi)gradients in policy evaluation and direct policy optimization. In…

Machine Learning · Computer Science 2023-06-21 Semih Cayci , Atilla Eryilmaz

The stochastic gradient descent (SGD) optimization algorithm plays a central role in a series of machine learning applications. The scientific literature provides a vast amount of upper error bounds for the SGD method. Much less attention…

Numerical Analysis · Mathematics 2020-10-05 Arnulf Jentzen , Philippe von Wurstemberger

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

Recent advances in vision-language-action (VLA) models for robotics have highlighted the importance of reliable uncertainty quantification in sequential tasks. However, assessing and improving calibration in such settings remains mostly…

Robotics · Computer Science 2026-04-23 Shelly Francis-Meretzki , Mirco Mutti , Yaniv Romano , Aviv Tamar

Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning. To date, however, most of the…

Machine Learning · Computer Science 2020-09-02 Xin Zhang , Jia Liu , Zhengyuan Zhu

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

In this paper, we study decentralized empirical risk minimization problems, where the goal is to minimize a finite-sum of smooth and strongly-convex functions available over a network of nodes. In this Part I, we propose…

Optimization and Control · Mathematics 2019-12-12 Ran Xin , Usman A. Khan , Soummya Kar

Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several…

Machine Learning · Computer Science 2019-06-10 Zhenxun Zhuang , Ashok Cutkosky , Francesco Orabona

In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the TD error is defined by a bootstrap method, its computation tends to be noisy and destabilize…

Machine Learning · Computer Science 2026-04-03 Taisuke Kobayashi

The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in which the data holders (such as government branches, private…

Machine Learning · Computer Science 2020-08-17 Bin Gu , An Xu , Zhouyuan Huo , Cheng Deng , Heng Huang

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Machine Learning · Computer Science 2016-04-06 Wei Zhang , Suyog Gupta , Xiangru Lian , Ji Liu

Differential temporal difference (TD) methods are value-based reinforcement learning algorithms that have been proposed for infinite-horizon problems. They rely on reward centering, where each reward is centered by the average reward. This…

Machine Learning · Computer Science 2026-05-07 Kris De Asis , Mohamed Elsayed , Jiamin He

The task of predicting long-term patient outcomes using supervised machine learning is a challenging one, in part because of the high variance of each patient's trajectory, which can result in the model over-fitting to the training data.…

Machine Learning · Computer Science 2026-02-09 Thomas Frost , Kezhi Li , Steve Harris

Recent empirical work on stochastic gradient descent (SGD) applied to over-parameterized deep learning has shown that most gradient components over epochs are quite small. Inspired by such observations, we rigorously study properties of…

Machine Learning · Computer Science 2021-10-19 Yingxue Zhou , Xinyan Li , Arindam Banerjee