English
Related papers

Related papers: New Versions of Gradient Temporal Difference Learn…

200 papers

We propose new continuous-time formulations for first-order stochastic optimization algorithms such as mini-batch gradient descent and variance-reduced methods. We exploit these continuous-time models, together with simple Lyapunov analysis…

Optimization and Control · Mathematics 2020-03-12 Antonio Orvieto , Aurelien Lucchi

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

In this paper we introduce the idea of improving the performance of parametric temporal-difference (TD) learning algorithms by selectively emphasizing or de-emphasizing their updates on different time steps. In particular, we show that…

Machine Learning · Computer Science 2016-07-21 Richard S. Sutton , A. Rupam Mahmood , Martha White

Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning under off-policy…

Artificial Intelligence · Computer Science 2019-03-04 Xiang Gu , Sina Ghiassian , Richard S. Sutton

The main aim of this paper is to provide an analysis of gradient descent (GD) algorithms with gradient errors that do not necessarily vanish, asymptotically. In particular, sufficient conditions are presented for both stability (almost sure…

Systems and Control · Computer Science 2017-09-19 Arunselvan Ramaswamy , Shalabh Bhatnagar

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such…

Machine Learning · Computer Science 2025-03-11 Vivek Myers , Chongyi Zheng , Anca Dragan , Sergey Levine , Benjamin Eysenbach

Devising and analyzing learning models for spatiotemporal network data is of importance for tasks including forecasting, anomaly detection, and multi-agent coordination, among others. Graph Convolutional Neural Networks (GCNNs) are an…

Machine Learning · Computer Science 2022-07-01 Mohammad Sabbaqi , Elvin Isufi

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor lambda. Currently the most important application of these methods is to temporal…

Artificial Intelligence · Computer Science 2008-02-03 P. Cichosz

In this paper, we propose a unified convergence analysis for a class of generic shuffling-type gradient methods for solving finite-sum optimization problems. Our analysis works with any sampling without replacement strategy and covers many…

Optimization and Control · Mathematics 2021-09-21 Lam M. Nguyen , Quoc Tran-Dinh , Dzung T. Phan , Phuong Ha Nguyen , Marten van Dijk

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

In this paper, a Gauss-Newton Temporal Difference (GNTD) learning method is proposed to solve the Q-learning problem with nonlinear function approximation. In each iteration, our method takes one Gauss-Newton (GN) step to optimize a variant…

Optimization and Control · Mathematics 2024-04-02 Zhifa Ke , Junyu Zhang , Zaiwen Wen

We propose a categorical semantics of gradient-based machine learning algorithms in terms of lenses, parametrised maps, and reverse derivative categories. This foundation provides a powerful explanatory and unifying framework: it…

Machine Learning · Computer Science 2021-07-14 G. S. H. Cruttwell , Bruno Gavranović , Neil Ghani , Paul Wilson , Fabio Zanasi

Topological learning is a wide research area aiming at uncovering the mutual spatial relationships between the elements of a set. Some of the most common and oldest approaches involve the use of unsupervised competitive neural networks.…

Machine Learning · Statistics 2021-11-03 Pietro Barbiero , Gabriele Ciravegna , Vincenzo Randazzo , Giansalvo Cirrincione

Attempt to fully discover the temporal diversity and chronological characteristics for self-supervised video representation learning, this work takes advantage of the temporal dependencies within videos and further proposes a novel…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Yang Liu , Keze Wang , Haoyuan Lan , Liang Lin

We consider distributed smooth nonconvex unconstrained optimization over networks, modeled as a connected graph. We examine the behavior of distributed gradient-based algorithms near strict saddle points. Specifically, we establish that (i)…

Optimization and Control · Mathematics 2020-05-26 Amir Daneshmand , Gesualdo Scutari , Vyacheslav Kungurtsev

We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation: to get an estimate…

Machine Learning · Statistics 2020-08-28 Antti Koskela , Antti Honkela

Federated learning faces critical challenges in balancing communication efficiency and model accuracy. One key issue lies in the approximation of update errors without incurring high computational costs. In this paper, we propose a…

Machine Learning · Computer Science 2025-05-29 Ganglou Xu

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

A fundamental notion of distance between train and test distributions from the field of domain adaptation is discrepancy distance. While in general hard to compute, here we provide the first set of provably efficient algorithms for testing…

Data Structures and Algorithms · Computer Science 2024-06-14 Gautam Chandrasekaran , Adam R. Klivans , Vasilis Kontonis , Konstantinos Stavropoulos , Arsen Vasilyan

This paper considers the problem of understanding the exit time for trajectories of gradient-related first-order methods from saddle neighborhoods under some initial boundary conditions. Given the 'flat' geometry around saddle points,…

Optimization and Control · Mathematics 2023-10-10 Rishabh Dixit , Mert Gurbuzbalaban , Waheed U. Bajwa