Machine Learning Theory
Faculty
- Courant Institute School of Mathematics, Computing, and Data Science: Joan Bruna, Carlos Fernandez-Granda, Yanjun Han, Arthur Jacot, Qi Lei, Mehryar Mohri, Jonathan Niles-Weed, Benjamin Peherstorfer, Rajesh Ranganath, Oded Regev, Matus Telgarsky, Eric Vanden-Eijnden, Andrew Wilson;
- Stern School of Business: Xi Chen;
- Tandon School of Engineering: Anna Choromanska, Pavel Izmailov, Christopher Musco;
-
Algorithms and Theory Group
Three key issues for an algorithm are: Is it correct? How efficient is it? Can one do better? Our strong and diverse group seeks provable answers to these questions. We focus on problems and questions in the following areas: complexity theory, cryptography, computational geometry, computational algebra, randomness (in algorithm design and average case analysis) and algorithmic game theory.
-
Computational Intelligence, Learning, Vision, and Robotics (CILVR)
The CILVR Lab (Computational Intelligence, Learning, Vision, and Robotics) regroups faculty members, research scientists, postdocs, and students working on AI, machine learning, and a wide variety of applications, notably computer perception, natural language understanding, robotics, and healthcare.
-
Data for Intelligent Computing and Engineering Lab
The Data for Intellingent Computing and Engineering Lab currently focuses on the following aspects of Machine Learning:Theoretical and applied aspects of Inverse Problems using Deep Learning, Physics-informed Machine Learning, Adversarial Machine Learning, Deep Reinforcement Learning, Distributed Machine Learning, and Autonomous Navigatio
