Program Synthesis meets Machine Learning by Sriram Rajamani

Location: CSA Seminar Hall (Room No. 254, First Floor)

Department of Computer Science and Automation
Department Seminar

Speaker : Sriram Rajamani

Title : Program Synthesis meets Machine Learning

Date : Friday, September 20, 2019

Time : 4:00 PM

Venue : CSA Seminar Hall (Room No. 254, First Floor)

Abstract

We give a tutorial overview of program synthesis, from its first formulation by Church in 1957, through its pragmatic evolution through sketching and programing-by-examples, and compare program synthesis with supervised machine learning. We then present our recent efforts (together with colleagues) in combining program synthesis and machine learning techniques to solve the problem of synthesizing extractors from heterogeneous data, as well as in solving NLP problems. Finally, we explore several opportunities at the intersection of program synthesis (and more broadly the PL  community) and machine learning, such as pruning and ranking programs during synthesis, neural program synthesis and automatic differentiation. Towards the end, we will briefly outline plans for a course we are planning with Prof. Deepak D’Souza and Prof. Chiranjib Bhattacharyya in the Jan 2020 semester on this broad topic.

Biography of the speaker

Sriram Rajamani is Distinguished Scientist and Managing Director of Microsoft Research India. His research interests are in designing, building and analyzing computer systems in a principled manner. Over the years he has worked on various topics including Hardware and Software Verification, Type Systems, Language Design, Distributed Systems, Security and Privacy. His current research interest is in combining Program Synthesis and Machine Learning.

Host Faculty : Deepak D’Souza

ALL ARE WELCOME
—