English
Related papers

Related papers: Finite-Time Error Bounds for Greedy-GQ

200 papers

Learning to optimize is an approach that leverages training data to accelerate the solution of optimization problems. Many approaches use unrolling to parametrize the update step and learn optimal parameters. Although L2O has shown…

Optimization and Control · Mathematics 2025-07-15 Patrick Fahy , Mohammad Golbabaee , Matthias J. Ehrhardt

We present a finite-time analysis of two smoothed functional stochastic approximation algorithms for simulation-based optimization. The first is a two time-scale gradient-based method, while the second is a three time-scale Newton-based…

Machine Learning · Computer Science 2026-04-01 Kaustubh Kartikey , Shalabh Bhatnagar

Despite empirical success, the theory of reinforcement learning (RL) with value function approximation remains fundamentally incomplete. Prior work has identified a variety of pathological behaviours that arise in RL algorithms that combine…

Machine Learning · Computer Science 2020-10-30 Kenny Young , Richard S. Sutton

A fundamental open problem in learning theory is to characterize the best-case teaching dimension $\operatorname{TS}_{\min}$ of a concept class $\mathcal{C}$ with finite VC dimension $d$. Resolving this problem will, in particular, settle…

Machine Learning · Statistics 2025-05-07 Spencer Compton , Chirag Pabbaraju , Nikita Zhivotovskiy

We present a simple performance bound for the greedy scheme in string optimization problems that obtains strong results. Our approach vastly generalizes the group of previously established greedy curvature bounds by Conforti and…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Brandon Van Over , Bowen Li , Edwin K. P. Chong , Ali Pezeshki

We study the fundamental problem of selecting optimal features for model construction. This problem is computationally challenging on large datasets, even with the use of greedy algorithm variants. To address this challenge, we extend the…

This paper is motivated by recent research in the $d$-dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampling and Greedy demonstrate promising empirical performance,…

Machine Learning · Computer Science 2025-05-20 Yuwei Luo , Mohsen Bayati

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

We study the worst-case adaptive optimization problem with budget constraint that is useful for modeling various practical applications in artificial intelligence and machine learning. We investigate the near-optimality of greedy algorithms…

Artificial Intelligence · Computer Science 2017-05-24 Nguyen Viet Cuong , Huan Xu

Orthogonal greedy learning (OGL) is a stepwise learning scheme that starts with selecting a new atom from a specified dictionary via the steepest gradient descent (SGD) and then builds the estimator through orthogonal projection. In this…

Machine Learning · Computer Science 2016-04-21 Lin Xu , Shaobo Lin , Jinshan Zeng , Xia Liu , Zongben Xu

Finding a minimum vertex cover in a network is a fundamental NP-complete graph problem. One way to deal with its computational hardness, is to trade the qualitative performance of an algorithm (allowing non-optimal outputs) for an improved…

Data Structures and Algorithms · Computer Science 2023-12-14 Thomas Bläsius , Tobias Friedrich , Maximilian Katzmann

This work introduces an empirical quadrature-based hyperreduction procedure and greedy training algorithm to effectively reduce the computational cost of solving convection-dominated problems with limited training. The proposed approach…

Numerical Analysis · Mathematics 2023-09-14 Marzieh Alireza Mirhoseini , Matthew J. Zahr

Orthogonal greedy learning (OGL) is a stepwise learning scheme that adds a new atom from a dictionary via the steepest gradient descent and build the estimator via orthogonal projecting the target function to the space spanned by the…

Machine Learning · Computer Science 2014-11-14 Lin Xu , Shaobo Lin , Jinshan Zeng , Zongben Xu

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

A q-Gauss-Newton algorithm is an iterative procedure that solves nonlinear unconstrained optimization problems based on minimization of the sum squared errors of the objective function residuals. Main advantage of the algorithm is that it…

Optimization and Control · Mathematics 2021-05-28 Danijela Protic , Miomir Stankovic

We present convergence estimates of two types of greedy algorithms in terms of the metric entropy of underlying compact sets. In the first part, we measure the error of a standard greedy reduced basis method for parametric PDEs by the…

Numerical Analysis · Mathematics 2024-10-29 Yuwen Li , Jonathan Siegel

Closeness is a widely-used centrality measure in social network analysis. For a node it indicates the reciprocal of the average shortest-path distance to the other nodes of the network. While the identification of the k nodes with highest…

Data Structures and Algorithms · Computer Science 2019-05-16 Elisabetta Bergamini , Tanya Gonser , Henning Meyerhenke

This paper provides a theoretical understanding of Deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning. Despite the tremendous empirical achievement of the DQN, its theoretical characterization…

Machine Learning · Computer Science 2023-10-26 Shuai Zhang , Hongkang Li , Meng Wang , Miao Liu , Pin-Yu Chen , Songtao Lu , Sijia Liu , Keerthiram Murugesan , Subhajit Chaudhury

Greedy Sampling Methods (GSMs) are widely used to construct approximate solutions of Configuration Optimization Problems (COPs), where a loss functional is minimized over finite configurations of points in a compact domain. While effective…

Optimization and Control · Mathematics 2026-01-09 Evie Nielen , Oliver Tse

In many prediction problems, it is not uncommon that the number of variables used to construct a forecast is of the same order of magnitude as the sample size, if not larger. We then face the problem of constructing a prediction in the…

Statistics Theory · Mathematics 2016-02-08 Alessio Sancetta
‹ Prev 1 4 5 6 7 8 10 Next ›