2026-09-19T01:28:02Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1569322024-09-25T04:03:13Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Pu, Yewen
Tenenbaum, Joshua B.
Acquaviva, Samuel
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
2024-09-24T18:21:27Z
2024-09-24T18:21:27Z
2024-05
2024-07-11T15:30:16.767Z
https://hdl.handle.net/1721.1/156932
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.
M.Eng.
Massachusetts Institute of Technology
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
https://creativecommons.org/licenses/by-nc-nd/4.0/
Overcoming the Expressivity-Efficiency Tradeoff in Program Induction
Thesis
application/pdf
Master
Master of Engineering in Computation and Cognition
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="16115f1e-17d4-405d-8150-9f86df1ef0a9">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Overcoming the Expressivity-Efficiency Tradeoff in Program Induction</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Acquaviva, Samuel</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by-nc-nd/4.0/</License>
<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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>