Program Synthesis with Symbolic Properties
Program synthesis is the task of automatically writing computer programs given a specification for their behavior. Program synthesis is challenging due to the combinatorial nature of the search space. In the short term, improving program synthesis could make people vastly more productive, by transfo...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2022
|
| Online Access: | https://hdl.handle.net/1721.1/143172 |
| _version_ | 1826192729747488768 |
|---|---|
| author | Sechopoulos, Theodoros |
| author2 | Tenenbaum, Joshua B. |
| author_facet | Tenenbaum, Joshua B. Sechopoulos, Theodoros |
| author_sort | Sechopoulos, Theodoros |
| collection | MIT |
| description | Program synthesis is the task of automatically writing computer programs given a specification for their behavior. Program synthesis is challenging due to the combinatorial nature of the search space. In the short term, improving program synthesis could make people vastly more productive, by transforming how they communicate with computers. In the long term, improving program synthesis could bring us a step closer to understanding human intelligence and to building machines with human-like intelligence. In this work we discuss how symbolic properties (which are themselves programs) can help program synthesis performance. Specifically, building on the formulation of properties in Odena and Sutton (2020) we present PropsimFit, a novel online synthesis algorithm that uses properties for program search and show that it outperforms naive non-property baselines in the Rule (2020) list function dataset. Finally, we discuss future ways to use properties for synthesis based on the insights gained from PropsimFit and its limitations. |
| first_indexed | 2024-09-23T09:28:20Z |
| format | Thesis |
| id | mit-1721.1/143172 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T09:28:20Z |
| publishDate | 2022 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1431722022-06-16T03:49:51Z Program Synthesis with Symbolic Properties Sechopoulos, Theodoros Tenenbaum, Joshua B. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Program synthesis is the task of automatically writing computer programs given a specification for their behavior. Program synthesis is challenging due to the combinatorial nature of the search space. In the short term, improving program synthesis could make people vastly more productive, by transforming how they communicate with computers. In the long term, improving program synthesis could bring us a step closer to understanding human intelligence and to building machines with human-like intelligence. In this work we discuss how symbolic properties (which are themselves programs) can help program synthesis performance. Specifically, building on the formulation of properties in Odena and Sutton (2020) we present PropsimFit, a novel online synthesis algorithm that uses properties for program search and show that it outperforms naive non-property baselines in the Rule (2020) list function dataset. Finally, we discuss future ways to use properties for synthesis based on the insights gained from PropsimFit and its limitations. M.Eng. 2022-06-15T13:01:16Z 2022-06-15T13:01:16Z 2022-02 2022-02-22T18:32:01.826Z Thesis https://hdl.handle.net/1721.1/143172 In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Sechopoulos, Theodoros Program Synthesis with Symbolic Properties |
| title | Program Synthesis with Symbolic Properties |
| title_full | Program Synthesis with Symbolic Properties |
| title_fullStr | Program Synthesis with Symbolic Properties |
| title_full_unstemmed | Program Synthesis with Symbolic Properties |
| title_short | Program Synthesis with Symbolic Properties |
| title_sort | program synthesis with symbolic properties |
| url | https://hdl.handle.net/1721.1/143172 |
| work_keys_str_mv | AT sechopoulostheodoros programsynthesiswithsymbolicproperties |