Please use this identifier to cite or link to this item:
|Title:||Data-driven approximations to NP-hard problems|
|Citation:||Proceedings of the 31st AAAI Conference on Artificial Intelligence, AAAI 2017, 2017 / pp.1453-1459|
|Conference Name:||Thirty-first AAAI Conference on Artificial Intelligence (AAAI-17) (04 Feb 2017 - 09 Feb 2017 : San Francisco)|
|Anton Milan, S. Hamid Rezatofighi, Ravi Garg, Anthony Dick, Ian Reid|
|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.|
|Rights:||Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.|
|Appears in Collections:||Australian Institute for Machine Learning publications|
Computer Science publications
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.