Prof. Aleksander Madry

Cadence Design Systems Professor of Electrical Engineering and Computer Science

Primary DLC

Department of Electrical Engineering and Computer Science

MIT Room: 32-G806

Areas of Interest and Expertise

Graph Theory Applications in OR/Scheduling
Communication Networks

Research Summary

Professor Mądry's research spans machine learning, optimization and algorithmic graph theory. In particular, IHe has a strong interest in building on the existing machine learning techniques to forge a decision-making toolkit that is reliable and well-understood enough to be safely and responsibly deployed in the real world.

The primary focus of Madry's lab is the science of modern machine learning. The aim is to combine theoretical and empirical insights to build a principled and thorough understanding of key techniques in machine learning, such as deep learning, as well as the challenges we face in this context. A major theme in the investigations is rethinking machine learning from the perspective of security, robustness and reliability.

Recent Work

  • Video

    2020 Frontiers of AI:ML - Aleksander Madry

    July 16, 2020Conference Video Duration: 39:7
    2020 Frontiers of AI:ML - Aleksander Madry


    Aleksander Madry - 2019 RD Conference

    November 20, 2019Conference Video Duration: 39:16

    Towards Deployable ML

    Machine learning has made tremendous progress over the last decade. It's thus tempting to believe that ML techniques are a "silver bullet", capable of making progress on any real-world problem they are applied to.

    But is that really so?

    In this talk, I will discuss a major challenge in the real-world deployment of ML: making ML solutions robust, reliable and secure. In particular, I will survey the widespread vulnerabilities of state-of-the-art ML models to various forms of noise, and then outline promising approach to alleviating these deficiencies as well as to making models be more human-aligned.

    2019 MIT Research and Development Conference