Holden Lee, Phillip Griffiths Assistant Research Professor

Contact Info:

Office Location:	605 West Chapel Hill Street, #521, Durham, NC 27701
Office Phone:	(609) 356-8523
Email Address:
Web Page:	http://holdenlee.github.io

Teaching (Spring 2021):

• MATH 230.03, PROBABILITY Synopsis

  Online ON, TuTh 05:15 PM-06:30 PM

  (also cross-listed as STA 230.03)

• MATH 730.03, PROBABILITY Synopsis

  Online ON, TuTh 05:15 PM-06:30 PM

Education:

Ph.D.

Princeton University

2019

Keywords:

Machine learning • Probability theory and stochastic processes

Recent Publications

1. Ge, R; Lee, H; Lu, J, Estimating normalizing constants for log-concave distributions: Algorithms and lower bounds, Proceedings of the Annual Acm Symposium on Theory of Computing (June, 2020), pp. 579-586 [doi]  [abs]
2. Kuditipudi, R; Wang, X; Lee, H; Zhang, Y; Li, Z; Hu, W; Arora, S; Ge, R, Explaining landscape connectivity of low-cost solutions for multilayer nets, Advances in Neural Information Processing Systems, vol. 32 (January, 2019)  [abs]
3. Lee, H; Mangoubi, O; Vishnoi, NK, Online Sampling from Log-Concave Distributions, Advances in Neural Information Processing Systems, vol. 32 (2019)
4. Ge, R; Lee, H; Risteski, A, Beyond log-concavity: Provable guarantees for sampling multi-modal distributions using simulated tempering langevin Monte Carlo, Advances in Neural Information Processing Systems, vol. 2018-December (January, 2018), pp. 7847-7856  [abs]