Saved in:
Bibliographic Details
Main Authors: Correia, Alvaro H. C., Worrall, Daniel E., Bondesan, Roberto
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2203.02201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914848876527616
author Correia, Alvaro H. C.
Worrall, Daniel E.
Bondesan, Roberto
author_facet Correia, Alvaro H. C.
Worrall, Daniel E.
Bondesan, Roberto
contents Simulated annealing (SA) is a stochastic global optimisation technique applicable to a wide range of discrete and continuous variable problems. Despite its simplicity, the development of an effective SA optimiser for a given problem hinges on a handful of carefully handpicked components; namely, neighbour proposal distribution and temperature annealing schedule. In this work, we view SA from a reinforcement learning perspective and frame the proposal distribution as a policy, which can be optimised for higher solution quality given a fixed computational budget. We demonstrate that this Neural SA with such a learnt proposal distribution, parametrised by small equivariant neural networks, outperforms SA baselines on a number of problems: Rosenbrock's function, the Knapsack problem, the Bin Packing problem, and the Travelling Salesperson problem. We also show that Neural SA scales well to large problems - generalising to significantly larger problems than the ones seen during training - while achieving comparable performance to popular off-the-shelf solvers and other machine learning methods in terms of solution quality and wall-clock time.
format Preprint
id arxiv_https___arxiv_org_abs_2203_02201
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Neural Simulated Annealing
Correia, Alvaro H. C.
Worrall, Daniel E.
Bondesan, Roberto
Machine Learning
Optimization and Control
Simulated annealing (SA) is a stochastic global optimisation technique applicable to a wide range of discrete and continuous variable problems. Despite its simplicity, the development of an effective SA optimiser for a given problem hinges on a handful of carefully handpicked components; namely, neighbour proposal distribution and temperature annealing schedule. In this work, we view SA from a reinforcement learning perspective and frame the proposal distribution as a policy, which can be optimised for higher solution quality given a fixed computational budget. We demonstrate that this Neural SA with such a learnt proposal distribution, parametrised by small equivariant neural networks, outperforms SA baselines on a number of problems: Rosenbrock's function, the Knapsack problem, the Bin Packing problem, and the Travelling Salesperson problem. We also show that Neural SA scales well to large problems - generalising to significantly larger problems than the ones seen during training - while achieving comparable performance to popular off-the-shelf solvers and other machine learning methods in terms of solution quality and wall-clock time.
title Neural Simulated Annealing
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2203.02201