AAAI Publications, Thirty-First AAAI Conference on Artificial Intelligence

Font Size: 
Data-Driven Approximations to NP-Hard Problems
Anton Milan, S. Hamid Rezatofighi, Ravi Garg, Anthony Dick, Ian Reid

Last modified: 2017-02-12


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.


Long short-term memory, data association, matching

Full Text: PDF