Machine Learning and Algorithmic Challenges with Aleksander Madry

In this episode

Aleksander Madry, Associate Professor at CSAIL, tackles key algorithmic challenges in today’s computing as part of his work in the Theory of Computation Group at CSAIL. His work is described as re-thinking machine learning from the perspective of security and robustness. Madry discusses the evolution of the human and machine interaction and provides insight on adoption of M/L systems over the next few years.

About the speakers

Associate Professor, MIT EECS

Aleksander Madry received his PhD at MIT in 2011. He spent a year as a postdoctoral researcher at Microsoft Research New England and later joined on the faculty of EPFL for almost three years. Now, Madry is an assistant in the MIT Electrical Engineering & Computer Science (EECS) Department and a member of the Theory of Computation group at MIT Computer Science Artificial Intelligence Laboratory (CSAIL). His work has been recognized with a number of awards including: NSF Career Award, Alfred P. Sloan Research Fellowship, ACM Doctoral Dissertation Award Honorable Mention, Geroge M. Sprowls Doctoral Dissertation Award, and a number of “best” paper awards at FOCS/SODA/STOC conferences.

Industry Impact
Aleksander Madry’s research is focused on two broad topics: algorithmic graph theory and coping with uncertainty in the context of optimization. This research aims to identify and tackle key algorithmic challenges in today’s computing. A recurrent theme in the research is combining the traditional (mostly combinational in nature), algorithmic toolkit with a variety of continuous optimization techniques to come up with new ways to approach classic questions in the field. The ultimate goal is to develop theoretical ideas and tools that will change the way optimization is approached- in respect to all shapes and forms within theory and in practice.EECS’s work improves the quality of life for the people throughout the world. From robots that perform with professional dance troupes to medical electronic devices that harvest energy from differences in body temperature. Other examples include, the World Wide Web (Sir Tim Berners-Lee, CSAIL), the conversion of analog of digital TV (Jae S. Lim, RLE), building more reliable grids through development of systems behavior algorithms, and new MRI scanning technologies (Elfar Adalsteinsson RLE).