Data-driven approximations to NP-hard problems

Date

2017

Authors

Milan, A.
Rezatofighi, S.
Garg, R.
Dick, A.
Reid, I.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, 2017, pp.1453-1459

Statement of Responsibility

Anton Milan, S. Hamid Rezatofighi, Ravi Garg, Anthony Dick, Ian Reid

Conference Name

Thirty-first AAAI Conference on Artificial Intelligence (AAAI-17) (4 Feb 2017 - 9 Feb 2017 : San Francisco)

Abstract

There exist a number of problem classes for which obtaining the exact solution becomes exponentially expensive with increasing problem size. The quadratic assignment problem (QAP) or the travelling salesman problem (TSP) are just two examples of such NP-hard problems. In practice, approximate algorithms are employed to obtain a suboptimal solution, where one must face a trade-off between computational complexity and solution quality. In this paper, we propose to learn to solve these problem from approximate examples, using recurrent neural networks (RNNs). Surprisingly, such architectures are capable of producing highly accurate solutions at minimal computational cost. Moreover, we introduce a simple, yet effective technique for improving the initial (weak) training set by incorporating the objective cost into the training procedure. We demonstrate the functionality of our approach on three exemplar applications: marginal distributions of a joint matching space, feature point matching and the travelling salesman problem. We show encouraging results on synthetic and real data in all three cases.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

License

Call number

Persistent link to this record