English
Related papers

Related papers: n-Step Temporal Difference Learning with Optimal n

200 papers

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are batch methods designed mainly based on the convex optimization, say, the…

Machine Learning · Statistics 2018-02-01 Ke Ma , Jinshan Zeng , Jiechao Xiong , Qianqian Xu , Xiaochun Cao , Wei Liu , Yuan Yao

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

Machine Learning · Computer Science 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic…

As the scales of data sets expand rapidly in some application scenarios, increasing efforts have been made to develop fast submodular maximization algorithms. This paper presents a currently the most efficient algorithm for maximizing…

Data Structures and Algorithms · Computer Science 2018-11-20 Teng Li , Hyo-Sang Shin , Antonios Tsourdos

To increase the training speed of distributed learning, recent years have witnessed a significant amount of interest in developing both synchronous and asynchronous distributed stochastic variance-reduced optimization methods. However, all…

Machine Learning · Computer Science 2022-08-30 Zhuqing Liu , Xin Zhang , Jia Liu

Using insight from numerical approximation of ODEs and the problem formulation and solution methodology of TD learning through a Galerkin relaxation, I propose a new class of TD learning algorithms. After applying the improved numerical…

Machine Learning · Computer Science 2021-04-21 Caleb Bowyer

For min-max optimization and variational inequalities problems (VIP) encountered in diverse machine learning tasks, Stochastic Extragradient (SEG) and Stochastic Gradient Descent Ascent (SGDA) have emerged as preeminent algorithms. Constant…

Machine Learning · Statistics 2023-06-30 Emmanouil-Vasileios Vlatakis-Gkaragkounis , Angeliki Giannou , Yudong Chen , Qiaomin Xie

Stochastic gradient descent (SGD) is one of the most widely used algorithms for large scale optimization problems. While classical theoretical analysis of SGD for convex problems studies (suffix) \emph{averages} of iterates and obtains…

Optimization and Control · Mathematics 2019-05-30 Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal…

Machine Learning · Computer Science 2025-09-05 Mahammad Humayoo

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

We study stochastic approximation procedures for approximately solving a $d$-dimensional linear fixed point equation based on observing a trajectory of length $n$ from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the…

Optimization and Control · Mathematics 2024-05-14 Wenlong Mou , Ashwin Pananjady , Martin J. Wainwright , Peter L. Bartlett

Spiking neural networks have gained significant attention due to their brain-like information processing capabilities. The use of surrogate gradients has made it possible to train spiking neural networks with backpropagation, leading to…

Neural and Evolutionary Computing · Computer Science 2023-05-24 Dongcheng Zhao , Guobin Shen , Yiting Dong , Yang Li , Yi Zeng

Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address…

Machine Learning · Computer Science 2018-09-10 Kristopher De Asis , Richard S. Sutton

Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent…

Machine Learning · Statistics 2018-10-30 Ashok Cutkosky , Robert Busa-Fekete

Motivated by applications of large embedding models, we study differentially private (DP) optimization problems under sparsity of individual gradients. We start with new near-optimal bounds for the classic mean estimation problem but with…

Machine Learning · Computer Science 2024-11-01 Badih Ghazi , Cristóbal Guzmán , Pritish Kamath , Ravi Kumar , Pasin Manurangsi

We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…

Machine Learning · Computer Science 2020-03-04 Achraf Bahamou , Donald Goldfarb

Temporal difference (TD) learning is a cornerstone reinforcement learning (RL) method for policy evaluation, where the goal is to estimate the value function of a Markov decision process under a fixed policy. While a substantial body of…

Machine Learning · Computer Science 2026-02-02 Donghwan Lee , Do Wan Kim

Temporal Difference learning or TD($\lambda$) is a fundamental algorithm in the field of reinforcement learning. However, setting TD's $\lambda$ parameter, which controls the timescale of TD updates, is generally left up to the…

Machine Learning · Computer Science 2017-01-02 Timothy A. Mann , Hugo Penedones , Shie Mannor , Todd Hester

This paper analyzes multi-step TD-learning algorithms within the `deadly triad' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that n-step TD-learning algorithms…

Systems and Control · Electrical Eng. & Systems 2024-04-09 Donghwan Lee

We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control policy, working together to discover the…

Optimization and Control · Mathematics 2020-01-13 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg