PLSE Seminar - Synthesizing Programs over Noisy Data

Speaker: Shivam Handa , MIT CSAIL

Date: Thursday, April 01, 2021

Time: 11:00 AM to 12:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: https://mit.zoom.us/j/93308858252

Event Type:

Room Description:

Host:

Contact: Eric H. Atkinson, eatkinson@csail.mit.edu

Relevant URL: http://people.csail.mit.edu/eatkinson/plse-seminar/seminars.html

Speaker URL: None

Speaker Photo:
None

Reminders to: plse-seminar@csail.mit.edu, seminars@csail.mit.edu, pl@csail.mit.edu

Reminder Subject: TALK: PLSE Seminar - Synthesizing Programs over Noisy Data

Title: Synthesizing Programs over Noisy Data

Abstract: I will present a new framework and associated synthesis algorithms for program synthesis over noisy data, i.e., data that may contain incorrect/corrupted input-output examples. Our framework is able to solve a variety of noisy program synthesis problems by formulating an optimization problem in terms of a Loss Function, a Complexity metric, and an Objective Function. Results from our implemented system running on problems from the SyGuS 2018 benchmark suite highlight its ability to successfully synthesize programs in the face of noisy data sets, including the ability to synthesize a correct program even when every input-output example in the data set is corrupted.
I will also discuss some theoretical results from our subsequent work. It defines the correctness of these synthesis algorithms in terms of their probability of synthesizing the correct hidden program. This allows us to formalize the concept of an Optimal Loss Function and formulate the convergence guarantees of a synthesis algorithm.

Research Areas:
Programming Languages & Software

Impact Areas:

This event is not part of a series.

Created by Eric H. Atkinson Email at Wednesday, March 24, 2021 at 3:39 PM.