Predictive Synthesis of API-Centric Code

Symposium on Machine Programming (MAPS) at PLDI

Abstract

Today’s programmers, especially data science practitioners, make heavy use of data-processing libraries (APIs) such as PyTorch, Tensorflow, NumPy, and the like. Program synthesizers can provide significant coding assistance to this community of users; however program synthesis also can be slow due to enormous search spaces.

In this work, we examine ways in which machine learning can be used to accelerate enumerative program synthesis. We present a deep-learning-based model to predict the sequence of API functions that would be needed to go from a given input to a desired output, both being numeric vectors. Our work is based on two insights. First, it is possible to learn, based on a large number of input-output examples, to predict the likely API function needed. Second, and importantly, it is also possible to learn to compose API functions into a sequence, given an input and the desired final output, without explicitly knowing the intermediate values.

We show that we can speed up an enumerative synthesizer by using predictions from our model variants. These speedups significantly outperform previous ways (e.g. DeepCoder [2]) in which researchers have used ML models in enumerative synthesis.

Latest Publications

Sustainable AI: Environmental Implications, Challenges and Opportunities

Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona Aga Behram, James Huang, Charles Bai, Michael Gschwind, Anurag Gupta, Myle Ott, Anastasia Melnikov, Salvatore Candido, David Brooks, Geeta Chauhan, Benjamin Lee, Hsien-Hsin S. Lee, Bugra Akyildiz, Max Balandat, Joe Spisak, Ravi Jain, Mike Rabbat, Kim Hazelwood

MLSys - 2022