Mądry Lab

Towards a Principled Science of Deep Learning

The primary focus of our lab is the science of deep learning. We aim to combine theoretical and empirical insights to build a principled and thorough understanding of key deep learning techniques as well as the challenges we face in this context. The list of topics we are currently exploring includes machine learning security (with an emphasis on adversarial robustness), and the power and limitations of unsupervised deep learning (with a focus on generative adversarial networks).

Github Twitter



Faculty: Aleksander Mądry

Graduate Students: Aleksandar Makelov, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, Kai Xiao

Undergraduate Students: Logan Engstrom, Nur Muhammad Shafiullah, Alexander Turner

Affiliated Researchers: Jerry Li, Ludwig Schmidt