English
Related papers

Related papers: R-GTD: A Geometric Analysis of Gradient Temporal-D…

200 papers

Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman…

Machine Learning · Computer Science 2014-06-13 Matthieu Geist , Olivier Pietquin

We study the Out-of-Distribution (OOD) generalization in machine learning and propose a general framework that establishes information-theoretic generalization bounds. Our framework interpolates freely between Integral Probability Metric…

Information Theory · Computer Science 2024-12-16 Wenliang Liu , Guanding Yu , Lele Wang , Renjie Liao

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

Despite an extensive body of literature on deep learning optimization, our current understanding of what makes an optimization algorithm effective is fragmented. In particular, we do not understand well whether enhanced optimization…

Machine Learning · Computer Science 2024-03-04 Toki Tahmid Inan , Mingrui Liu , Amarda Shehu

Linear TD($\lambda$) is one of the most fundamental reinforcement learning algorithms for policy evaluation. Previously, convergence rates are typically established under the assumption of linearly independent features, which does not hold…

Machine Learning · Computer Science 2025-10-15 Zixuan Xie , Xinyu Liu , Rohan Chandra , Shangtong Zhang

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

In reinforcement learning (RL), Q-learning is a fundamental algorithm whose convergence is guaranteed in the tabular setting. However, this convergence guarantee does not hold under linear function approximation. To overcome this…

Machine Learning · Computer Science 2026-02-04 Hyukjun Yang , Han-Dong Lim , Donghwan Lee

We develop a general framework unifying several gradient-based stochastic optimization methods for empirical risk minimization problems both in centralized and distributed scenarios. The framework hinges on the introduction of an augmented…

Optimization and Control · Mathematics 2022-07-11 Yan Huang , Ying Sun , Zehan Zhu , Changzhi Yan , Jinming Xu

This work proposes an algorithmic framework to learn time-varying graphs from online data. The generality offered by the framework renders it model-independent, i.e., it can be theoretically analyzed in its abstract formulation and then…

Machine Learning · Computer Science 2022-05-25 Alberto Natali , Elvin Isufi , Mario Coutino , Geert Leus

Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement…

Machine Learning · Computer Science 2018-11-07 Jalaj Bhandari , Daniel Russo , Raghav Singal

An influential line of recent work has focused on the generalization properties of unregularized gradient-based learning procedures applied to separable linear classification with exponentially-tailed loss functions. The ability of such…

Machine Learning · Computer Science 2022-06-24 Matan Schliserman , Tomer Koren

The decentralized gradient descent (DGD) algorithm, and its sibling, diffusion, are workhorses in decentralized machine learning, distributed inference and estimation, and multi-agent coordination. We propose a novel, principled framework…

Signal Processing · Electrical Eng. & Systems 2025-06-04 Erik G. Larsson , Nicolo Michelusi

We present a new algorithm for solving optimization problems with objective functions that are the sum of a smooth function and a (potentially) nonsmooth regularization function, and nonlinear equality constraints. The algorithm may be…

Optimization and Control · Mathematics 2024-04-12 Yutong Dai , Xiaoyi Qu , Daniel P. Robinson

Temporal-difference learning is a popular algorithm for policy evaluation. In this paper, we study the convergence of the regularized non-parametric TD(0) algorithm, in both the independent and Markovian observation settings. In particular,…

Optimization and Control · Mathematics 2022-05-25 Eloïse Berthier , Ziad Kobeissi , Francis Bach

The endeavor of artificial intelligence (AI) is to design autonomous agents capable of achieving complex tasks. Namely, reinforcement learning (RL) proposes a theoretical background to learn optimal behaviors. In practice, RL algorithms…

Machine Learning · Computer Science 2022-09-27 Firas Jarboui , Ahmed Akakzia

The flexibility of decision boundaries in neural networks that are unguided by training data is a well-known problem typically resolved with generalization methods. A surprising result from recent knowledge distillation (KD) literature is…

Machine Learning · Computer Science 2024-10-28 HeeSeung Jung , Kangil Kim , Hoyong Kim , Jong-Hun Shin

In this article, we propose a new approach, optimize then agree for minimizing a sum $ f = \sum_{i=1}^n f_i(x)$ of convex objective functions over a directed graph. The optimize then agree approach decouples the optimization step and the…

Systems and Control · Electrical Eng. & Systems 2021-05-27 Vivek Khatana , Govind Saraswat , Sourav Patel , Murti V. Salapaka

Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to…

Machine Learning · Computer Science 2026-01-06 Ze Peng , Jian Zhang , Yisen Wang , Lei Qi , Yinghuan Shi , Yang Gao

Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attributed to distribution shifts, including user, character, and dialogue compositional shifts.…

Machine Learning · Computer Science 2026-04-14 Yongqi Li , Hao Lang , Fei Huang , Tieyun Qian , Yongbin Li

Modern machine learning relies on a collection of empirically successful but theoretically heterogeneous regularization techniques, such as weight decay, dropout, and exponential moving averages. At the same time, the rapidly increasing…

Machine Learning · Computer Science 2026-01-27 Laurent Caraffa