2020/07/07 by Yujia Li, Li, Yujia, Felix Gimeno +5 · 2 voices · 19 citations
Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Computer science #Field (mathematics) #Generalization #Imitation #Knapsack problem #Machine Learning and Algorithms #Machine learning #Mathematics #Reinforcement Learning in Robotics #Reinforcement learning #Robot Manipulation and Learning #Sorting #Theoretical computer science #Variety (cybernetics) #cs.AI #cs.LG #cs.NE #sort #stat.ML
paper · pdf · doi:10.48550/arxiv.2007.03629
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2020/07/07 · arxiv created 2020/07/08 · arxiv updated 2020/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program efficiency metrics, and discover new algorithms that surpass the teacher used in imitation. With this, our approach can learn to outperform custom-written solutions for a variety of problems, as we tested it on sorting, searching in ordered lists and the NP-complete 0/1 knapsack problem, which sets a notable milestone in the field of Neural Program Induction. As highlights, our learned model can perform sorting perfectly on any input data size we tested on, with O(n log n) complexity, whilst outperforming hand-coded algorithms, including quick sort, in number of operations even for list sizes far beyond those seen during training.