Learning TSP Requires Rethinking Generalization

06/12/2020 ∙ by Chaitanya K. Joshi, et al. ∙ 36

End-to-end training of neural network solvers for combinatorial problems such as the Travelling Salesman Problem is intractable and inefficient beyond a few hundreds of nodes. While state-of-the-art Machine Learning approaches perform closely to classical solvers for trivially small sizes, they are unable to generalize the learnt policy to larger instances of practical scales. Towards leveraging transfer learning to solve large-scale TSPs, this paper identifies inductive biases, model architectures and learning algorithms that promote generalization to instances larger than those seen in training. Our controlled experiments provide the first principled investigation into such zero-shot generalization, revealing that extrapolating beyond training data requires rethinking the entire neural combinatorial optimization pipeline, from network layers and learning paradigms to evaluation protocols.



There are no comments yet.


page 19

page 21

page 22

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.