Overcoming the Expressivity-Efficiency Tradeoff in Program Induction
Name
acquaviva-samacqua-meng-bcs-2024-thesis.pdf
Description
Thesis PDF
Size
906.79 KB
Format
Adobe PDF
Checksum (MD5)
f4a791cc1982e94f19b31f5289d214c7
Author(s)
Acquaviva, Samuel
Advisor(s)
Pu, Yewen
Tenenbaum, Joshua B.
Date Issued
May 2024
Publisher
Massachusetts Institute of Technology
Abstract
People are incredibly flexible and efficient inductive reasoners. On the other hand, current approaches in program synthesis show strong domain-specific performance, but are both less sample-efficient and less flexible. Large language models improve upon this sample-efficiency and domain-generality, but lack robustness and still fall far short of people and traditional approaches on difficult induction tasks. In this thesis, we propose two hypotheses for how people seemingly overcome this trade-off between flexibility and efficiency. In the first, we propose that people may operate over an incredibly vast language which is made tractable via a strong, bottom-up proposal model. In the second, we propose that, alternatively, people may relax the necessity of such a strong proposal model by learning task-specific reasoning languages through experience. We build models operationalizing both hypotheses and show that they can improve the generality and efficiency of previous models.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
Persistent DSpace Link
