Differentiable Program Learning with an Admissible Neural Heuristic

Simple item page
dc.contributor.advisorJermaine, Chrisen_US
dc.contributor.advisorChaudhuri, Swaraten_US
dc.creatorShah, Ameeshen_US
dc.date.accessioned2020-08-11T21:50:05Zen_US
dc.date.available2020-08-11T21:50:05Zen_US
dc.date.created2020-08en_US
dc.date.issued2020-08-11en_US
dc.date.submittedAugust 2020en_US
dc.date.updated2020-08-11T21:50:06Zen_US
dc.description.abstractWe study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and interpretability; however, learning them requires optimizing over a combinatorial space of program “architectures”. We frame this optimization problem as a search in a weighted graph whose paths encode top-down derivations of program syntax. Our key innovation is to view various classes of neural networks as continuous relaxations over the space of programs, which can then be used to complete any partial program. This relaxed program is differentiable and can be trained end-to-end, and the resulting training loss is an approximately admissible heuristic that can guide the combinatorial search. We instantiate our approach on top of the A* algorithm and an iteratively deepened branch-and-bound search, and use these algorithms to learn programmatic classifiers in three sequence classification tasks. Our experiments show that the algorithms outperform state-of-the-art methods for program learning, and that they discover programmatic classifiers that yield natural interpretations and achieve competitive accuracy.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationShah, Ameesh. "Differentiable Program Learning with an Admissible Neural Heuristic." (2020) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/109184">https://hdl.handle.net/1911/109184</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/109184en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectMachine Learningen_US
dc.subjectProgram Synthesisen_US
dc.subjectFunctional Programmingen_US
dc.subjectDifferentiable Progammingen_US
dc.titleDifferentiable Program Learning with an Admissible Neural Heuristicen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentComputer Scienceen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SHAH-DOCUMENT-2020.pdf
Size:
2.15 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.6 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations