Design of algorithms and machines capable of “intelligent” comprehension and decision making is one of the major scientific and technological challenges of this century. It is also a challenge for mathematics because it calls for new paradigms for mathematical reasoning, such as formalizing the “meaning” or “information content” of a piece of text or an image or scientific data. It is a challenge for mathematical optimization because the algorithms involved must scale to very large input sizes. It is a challenge for theoretical computer science because the obvious ways of formalizing many computational tasks in machine learning are provably intractable in a worst-case sense, and thus calls for new modes of analysis.
This program in theoretical machine learning at the IAS seeks to address such foundational issues. Started at the School of Mathematics in September 2017 as a natural extension of existing activities in Computer Science and Discrete Mathematics (CSDM), it is led by Sanjeev Arora, who holds a joint appointment at Princeton University and a long-term Visitor Professorship at the IAS. The program also includes two postdocs and visiting faculty. It also has close links and joint seminars with research groups at Princeton University, including Theoretical Machine Learning, Theoretical Computer Science, Program in Applied and Computational Math, and Operations Research. There are also ongoing collaborations with researchers seeking to apply machine learning towards understanding large data sets in areas such as social sciences, natural language processing, and neuroscience.
Visiting Professor & Members
- Sanjeev Arora, Visiting Professor, 2017-2019; Distinguished Visiting Professor, 2019-2020
- Nadav Cohen, Member, 2017-2018
- Behnam Neyshabur, Member, 2017-2018
- Sida Wang, Member, 2018-2019
- Richard Zemel, Visitor, Fall 2018
Important announcement: The Institute will have a one-year special program on this topic in 2019-2020, with over 15 visiting scientists.