Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Daokuan, Xu, Tianqi, Lu, Jie
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2311.08827
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910285987577856
author Zhu, Daokuan
Xu, Tianqi
Lu, Jie
author_facet Zhu, Daokuan
Xu, Tianqi
Lu, Jie
contents In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a given specific problem. In this paper, we propose a learning-based method to achieve efficient distributed optimization over networked systems. Specifically, a deep reinforcement learning (DRL) framework is developed for adaptive configuration within a parameterized unifying algorithmic form, which incorporates an abundance of decentralized first-order and second-order optimization algorithms. We exploit the local consensus and objective information to represent the regularities of problem instances and trace the solving progress, which constitute the states observed by a DRL agent. The framework is trained using Proximal Policy Optimization (PPO) on a number of practical problem instances of similar structures yet different problem data. Experiments on various smooth and non-smooth classes of objective functions demonstrate that our proposed learning-based method outperforms several state-of-the-art distributed optimization algorithms in terms of convergence speed and solution accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08827
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Deep Reinforcement Learning Approach to Efficient Distributed Optimization
Zhu, Daokuan
Xu, Tianqi
Lu, Jie
Optimization and Control
In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a given specific problem. In this paper, we propose a learning-based method to achieve efficient distributed optimization over networked systems. Specifically, a deep reinforcement learning (DRL) framework is developed for adaptive configuration within a parameterized unifying algorithmic form, which incorporates an abundance of decentralized first-order and second-order optimization algorithms. We exploit the local consensus and objective information to represent the regularities of problem instances and trace the solving progress, which constitute the states observed by a DRL agent. The framework is trained using Proximal Policy Optimization (PPO) on a number of practical problem instances of similar structures yet different problem data. Experiments on various smooth and non-smooth classes of objective functions demonstrate that our proposed learning-based method outperforms several state-of-the-art distributed optimization algorithms in terms of convergence speed and solution accuracy.
title A Deep Reinforcement Learning Approach to Efficient Distributed Optimization
topic Optimization and Control
url https://arxiv.org/abs/2311.08827