English
Related papers

Related papers: Constant Stepsize Q-learning: Distributional Conve…

200 papers

This paper investigates the supervised learning problem with observations drawn from certain general stationary stochastic processes. Here by \emph{general}, we mean that many stationary stochastic processes can be included. We show that…

Machine Learning · Statistics 2016-05-11 Hanyuan Hang , Yunlong Feng , Ingo Steinwart , Johan A. K. Suykens

Due to the limited number of bits in floating-point or fixed-point arithmetic, rounding is a necessary step in many computations. Although rounding methods can be tailored for different applications, round-off errors are generally…

Numerical Analysis · Mathematics 2020-06-02 Lu Xia , Martijn Anthonissen , Michiel Hochstenbach , Barry Koren

Stochastic approximation (SA) with multiple coupled sequences has found broad applications in machine learning such as bilevel learning and reinforcement learning (RL). In this paper, we study the finite-time convergence of nonlinear SA…

Machine Learning · Computer Science 2022-06-22 Han Shen , Tianyi Chen

In learning-to-learn the goal is to infer a learning algorithm that works well on a class of tasks sampled from an unknown meta distribution. In contrast to previous work on batch learning-to-learn, we consider a scenario where tasks are…

Machine Learning · Statistics 2018-03-23 Giulia Denevi , Carlo Ciliberto , Dimitris Stamos , Massimiliano Pontil

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size…

Machine Learning · Computer Science 2024-02-01 Thomas Degris , Khurram Javed , Arsalan Sharifnassab , Yuxin Liu , Richard Sutton

We present a simple picture of the training process of joint embedding self-supervised learning methods. We find that these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated…

Machine Learning · Computer Science 2023-05-31 James B. Simon , Maksis Knutins , Liu Ziyin , Daniel Geisz , Abraham J. Fetterman , Joshua Albrecht

$Q$-learning is one of the most fundamental reinforcement learning (RL) algorithms. Despite its widespread success in various applications, it is prone to overestimation bias in the $Q$-learning update. To address this issue, double…

Machine Learning · Computer Science 2026-01-13 Hyunjun Na , Donghwan Lee

In this paper, we consider distributed algorithms for solving the empirical risk minimization problem under the master/worker communication model. We develop a distributed asynchronous quasi-Newton algorithm that can achieve superlinear…

Optimization and Control · Mathematics 2019-06-11 Saeed Soori , Konstantin Mischenko , Aryan Mokhtari , Maryam Mehri Dehnavi , Mert Gurbuzbalaban

For many machine learning problems, data is abundant and it may be prohibitive to make multiple passes through the full training set. In this context, we investigate strategies for dynamically increasing the effective sample size, when…

Machine Learning · Computer Science 2016-10-10 Hadi Daneshmand , Aurelien Lucchi , Thomas Hofmann

$Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work…

Machine Learning · Computer Science 2025-05-28 Xinyu Liu , Zixuan Xie , Shangtong Zhang

We study gradient descent (GD) with a constant stepsize for $\ell_2$-regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensure monotonic reduction of the optimization objective,…

Machine Learning · Statistics 2025-11-04 Jingfeng Wu , Pierre Marion , Peter Bartlett

This paper studies the problem of risk-sensitive reinforcement learning (RSRL) in continuous time, where the environment is characterized by a controllable stochastic differential equation (SDE) and the objective is a potentially nonlinear…

Machine Learning · Computer Science 2025-12-03 Chuhan Xie

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized…

Machine Learning · Computer Science 2025-06-24 Hwanwoo Kim , Panos Toulis , Eric Laber

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide idealistic probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by…

Machine Learning · Computer Science 2021-10-27 Aaron Kandel , Scott J. Moura

We consider the problem of distributed learning, where a network of agents collectively aim to agree on a hypothesis that best explains a set of distributed observations of conditionally independent random processes. We propose a…

Optimization and Control · Mathematics 2017-04-12 Angelia Nedić , Alex Olshevsky , César A. Uribe

This paper studies fixed step-size stochastic approximation (SA) schemes, including stochastic gradient schemes, in a Riemannian framework. It is motivated by several applications, where geodesics can be computed explicitly, and their use…

Machine Learning · Statistics 2021-02-22 Alain Durmus , Pablo Jiménez , Éric Moulines , Salem Said

Deep reinforcement learning (DRL) has significantly advanced the field of combinatorial optimization (CO). However, its practicality is hindered by the necessity for a large number of reward evaluations, especially in scenarios involving…

Machine Learning · Computer Science 2024-07-18 Hyeonah Kim , Minsu Kim , Sungsoo Ahn , Jinkyoo Park

We obtain an expansion of the implicit weak discretization error for the target of stochastic approximation algorithms introduced and studied in [Frikha2013]. This allows us to extend and develop the Richardson-Romberg extrapolation method…

Probability · Mathematics 2015-03-10 Noufel Frikha , Lorick Huang

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

Machine Learning · Computer Science 2020-11-24 Joel Jang , Yoonjeon Kim , Kyoungho Choi , Sungho Suh

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…

Machine Learning · Computer Science 2024-09-02 Talha Bozkus , Urbashi Mitra