English
Related papers

Related papers: Convex Q-Learning, Part 1: Deterministic Optimal C…

200 papers

We consider a general class of regression models with normally distributed covariates, and the associated nonconvex problem of fitting these models from data. We develop a general recipe for analyzing the convergence of iterative algorithms…

Optimization and Control · Mathematics 2021-09-22 Kabir Aladin Chandrasekher , Ashwin Pananjady , Christos Thrampoulidis

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…

Machine Learning · Computer Science 2020-08-20 Aviral Kumar , Aurick Zhou , George Tucker , Sergey Levine

In temporal difference (TD) learning, off-policy sampling is known to be more practical than on-policy sampling, and by decoupling learning from data collection, it enables data reuse. It is known that policy evaluation (including…

Machine Learning · Computer Science 2021-06-25 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

We prove that a single-layer neural network trained with the Q-learning algorithm converges in distribution to a random ordinary differential equation as the size of the model and the number of training steps become large. Analysis of the…

Machine Learning · Computer Science 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

Unsupervised learning is the most challenging problem in machine learning and especially in deep learning. Among many scenarios, we study an unsupervised learning problem of high economic value --- learning to predict without costly pairing…

Machine Learning · Computer Science 2016-06-16 Jianshu Chen , Po-Sen Huang , Xiaodong He , Jianfeng Gao , Li Deng

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

Neural networks (NNs) have been extremely successful across many tasks in machine learning. Quantization of NN weights has become an important topic due to its impact on their energy efficiency, inference time and deployment on hardware.…

Machine Learning · Computer Science 2021-05-06 Burak Bartan , Mert Pilanci

Conventional optimization methods in machine learning and controls rely heavily on first-order update rules. Selecting the right method and hyperparameters for a particular task often involves trial-and-error or practitioner intuition,…

Machine Learning · Computer Science 2023-03-31 Tanmay Gautam , Samuel Pfrommer , Somayeh Sojoudi

Solving nonlinear optimal control problems is a challenging task, particularly for high-dimensional problems. We propose algorithms for model-based policy iterations to solve nonlinear optimal control problems with convergence guarantees.…

Systems and Control · Electrical Eng. & Systems 2026-03-17 Yiming Meng , Ruikun Zhou , Amartya Mukherjee , Maxwell Fitzsimmons , Christopher Song , Jun Liu

Quadratic assignment problems are a fundamental class of combinatorial optimization problems which are ubiquitous in applications, yet their exact resolution is NP-hard. To circumvent this impasse, it was proposed to regularize such…

Optimization and Control · Mathematics 2025-09-25 Venkatkrishna Karumanchi , Gabriel Rioux , Ziv Goldfeld

Motivated by applications arising from large scale optimization and machine learning, we consider stochastic quasi-Newton (SQN) methods for solving unconstrained convex optimization problems. The convergence analysis of the SQN methods,…

Optimization and Control · Mathematics 2019-10-02 Farzad Yousefian , Angelia Nedić , Uday Shanbhag

In this paper, we present a novel sufficient condition for the stability of discrete-time linear systems that can be represented as a set of piecewise linear constraints, which make them suitable for quadratic programming optimization…

Systems and Control · Electrical Eng. & Systems 2024-04-25 Marc Mitjans , Liangting Wu , Roberto Tron

Quadratic constrained quadratic programming problems often occur in various fields such as engineering practice, management science, and network communication. This article mainly studies a non convex quadratic programming problem with…

Optimization and Control · Mathematics 2023-12-29 Bo Zhang , YueLin Gao , Xia Liu , XiaoLi Huang

We consider the problem of reinforcement learning using function approximation, where the approximating basis can change dynamically while interacting with the environment. A motivation for such an approach is maximizing the value function…

Machine Learning · Computer Science 2010-05-04 Dotan Di Castro , Shie Mannor

In this paper, we introduce a unified framework for analyzing a large family of Q-learning algorithms, based on switching system perspectives and ODE-based stochastic approximation. We show that the nonlinear ODE models associated with…

Optimization and Control · Mathematics 2021-02-18 Donghwan Lee , Niao He

We propose a random coordinate descent algorithm for optimizing a non-convex objective function subject to one linear constraint and simple bounds on the variables. Although it is common use to update only two random coordinates…

Optimization and Control · Mathematics 2024-08-27 Alireza Ghaffari-Hadigheh , Lennart Sinjorgo , Renata Sotirov

We analyze worst-case convergence guarantees of first-order optimization methods over a function class extending that of smooth and convex functions. This class contains convex functions that admit a simple quadratic upper bound. Its study…

Optimization and Control · Mathematics 2022-05-31 Baptiste Goujaud , Adrien Taylor , Aymeric Dieuleveut

Discrete time stochastic optimal control problems and Markov decision processes (MDPs), respectively, serve as fundamental models for problems that involve sequential decision making under uncertainty and as such constitute the theoretical…

Optimization and Control · Mathematics 2023-03-08 Christian Beck , Arnulf Jentzen , Konrad Kleinberg , Thomas Kruse

We consider the problem of synthesizing optimal linear feedback policies subject to arbitrary convex constraints on the feedback matrix. This is known to be a hard problem in the usual formulations ($\Htwo,\Hinf,\LQR$) and previous works…

Systems and Control · Computer Science 2013-10-28 Krishnamurthy Dvijotham , Emanuel Todorov , Maryam Fazel

Federated learning enables training on a massive number of edge devices. To improve flexibility and scalability, we propose a new asynchronous federated optimization algorithm. We prove that the proposed approach has near-linear convergence…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-12-08 Cong Xie , Sanmi Koyejo , Indranil Gupta