Adam Klivans
Professor
Research
Research Areas:
Research Interests:
- Learning Theory
- Computational Complexity
- Pseudorandomness
- Limit Theorems
- Gaussian Space
Select Publications
2020. Approximation Schemes for Relu Regression. COLT.
.2020. Superpolynomial Lower Bounds for Learning One Layer Neural Networks Using Gradient Descent. ICML.
.2019. List-Decodable Linear Regression. NeurIPS.(Spotlight).
.2019. Time/Accuracy Tradeoffs for Learning a ReLU with Gaussian Marginals. NeurIPS.(Spotlight).
.2019. Learning Neural Networks with Two Nonlinear Layers in Polynomial-Time. COLT.
.Awards & Honors
- 2019 - Member, IAS School of Mathematics
- 2019 - Two Spotlight Presentations, NeurIPS 2019
- 2018 - Long-Term Participant, Simons Institute Program on Foundations of Deep Learning
- 2017 - Microsoft Azure Data Science Initiative Award
- 2013 - College of Natural Sciences Teaching Excellence
- 2011 - Research Professorship, MSRI
- 2007 - NSF CAREER Award
- 2006 - Best Student Paper Award, COLT
- 2004 - NSF Mathematical Postdoctoral Research Fellowship
- 1997 - Andrew Carnegie Presidential Scholar