Nadav Cohen

 

Nadav Cohen, Ph.D.
School of Mathematics
Institute for Advanced Study
Princeton, New Jersey
E-mail: cohennadav@ias.edu
Office: MOS-106, 1 Einstein Dr, Princeton, NJ

News

Research

My research focuses on the theoretical and algorithmic foundations of deep learning. In particular, I am interested in mathematically analyzing aspects of expressiveness, optimization and generalization, with the goal of deriving theoretically founded procedures and algorithms that will improve practical performance.

Blog Posts

Selected Talks

  • Simons Institute Workshop on Frontiers of Deep Learning 2019 (Berkeley, CA, USA): [video|slides]

  • ICERM Workshop on Theory and Practice in Machine Learning and Computer Vision 2019 (Providence, RI, USA): [video|slides]

  • ICML 2018 (Stockholm, Sweden): [video|slides]

  • ICLR 2018 (Vancouver, Canada): [video|slides]

  • Symposium on the Mathematical Theory of Deep Neural Networks 2018 (Princeton, NJ, USA): [video|slides]

  • Symposium on Physics and Machine Learning 2017 (New York City, NY, USA): [slides]

  • Mathematics of Deep Learning Workshop 2017 (Berlin, Germany): [slides]

  • AAAI Spring Symposium Series 2017 (Palo Alto, CA, USA): [slides]

  • CVPR 2017 (Honolulu, HI, USA): [slides]

  • GAMM 2017 (Weimar, Germany): [slides]

  • NIPS 2016 (Barcelona, Spain): [slides]

  • ICML 2016 (New York City, NY, USA): [video|slides]

  • COLT 2016 (New York City, NY, USA): [video|slides]