Sampling for Bayesian program learning
Name
6082-sampling-for-bayesian-program-learning.pdf
Size
383.7 KB
Format
Adobe PDF
Checksum (MD5)
e83aa5d14712a5f4ad95310a995a324d
Author(s)
Ellis, Kevin M.
Solar Lezama, Armando
Tenenbaum, Joshua B
Date Issued
2016
Journal
Advances in Neural Information Processing Systems (NIPS)
Publisher
Neural Information Processing Systems Foundation
Citation
Kevin Ellis et al. "Sampling for Bayesian program learning." Advances in Neural Information Processing Systems (NIPS) (2016) © 2016 Neural Information Processing Systems Foundation
Version
Final published version
Abstract
Towards learning programs from data, we introduce the problem of sampling programs from posterior distributions conditioned on that data. Within this setting, we propose an algorithm that uses a symbolic solver to efficiently sample programs. The proposal combines constraint-based program synthesis with sampling via random parity constraints. We give theoretical guarantees on how well the samples approximate the true posterior, and have empirical results showing the algorithm is efficient in practice, evaluating our approach on 22 program learning problems in the domains of text editing and computer-aided programming.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/6082-sampling-for-bayesian-program-learning
