Differentiable Program Learning with an Admissible Neural Heuristic

Simple item page
dc.contributor.advisorJermaine, Chris
dc.contributor.advisorChaudhuri, Swarat
dc.creatorShah, Ameesh
dc.date.accessioned2020-08-11T21:50:05Z
dc.date.available2020-08-11T21:50:05Z
dc.date.created2020-08
dc.date.issued2020-08-11
dc.date.submittedAugust 2020
dc.date.updated2020-08-11T21:50:06Z
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.
dc.format.mimetypeapplication/pdf
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>.
dc.identifier.urihttps://hdl.handle.net/1911/109184
dc.language.isoeng
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.
dc.subjectMachine Learning
dc.subjectProgram Synthesis
dc.subjectFunctional Programming
dc.subjectDifferentiable Progamming
dc.titleDifferentiable Program Learning with an Admissible Neural Heuristic
dc.typeThesis
dc.type.materialText
thesis.degree.departmentComputer Science
thesis.degree.disciplineEngineering
thesis.degree.grantorRice University
thesis.degree.levelMasters
thesis.degree.nameMaster of Science
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 Electronic Theses and Dissertations