Sample Complexity Bounds for Recurrent Neural Networks with Application to Combinatorial Graph Problems
Abstract
Learning to predict solutions to real-valued combinatorial graph problems promises efficient approximations. As demonstrated based on the NP-hard edge clique cover number, recurrent neural networks (RNNs) are particularly suited for this task and can even outperform state-of-the-art heuristics. However, the theoretical framework for estimating real-valued RNNs is understood only poorly. As our primary contribution, this is the first work that upper bounds the sample complexity for learning real-valued RNNs. While such derivations have been made earlier for feed-forward and convolutional neural networks, our work presents the first such attempt for recurrent neural networks. Given a single-layer RNN with $a$ rectified linear units and input of length $b$, we show that a population prediction error of $\varepsilon$ can be realized with at most $\tilde{\mathcal{O}}(a^4b/\varepsilon^2)$ samples. We further derive comparable results for multi-layer RNNs. Accordingly, a size-adaptive RNN fed with graphs of at most $n$ vertices can be learned in $\tilde{\mathcal{O}}(n^6/\varepsilon^2)$, i.e., with only a polynomial number of samples. For combinatorial graph problems, this provides a theoretical foundation that renders RNNs competitive.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2019
- DOI:
- arXiv:
- arXiv:1901.10289
- Bibcode:
- 2019arXiv190110289A
- Keywords:
-
- Statistics - Machine Learning;
- Computer Science - Machine Learning
- E-Print:
- A two-page summary of this paper has been accepted as a student abstract at AAAI-20, this is the extended full version