Holden Lee
Holden Lee
Postdoc in mathematics, Duke University
Verified email at duke.edu - Homepage
Cited by
Cited by
On the ability of neural nets to express distributions
H Lee, R Ge, T Ma, A Risteski, S Arora
Conference on Learning Theory 2017., 2017
Spectral filtering for general linear dynamical systems
E Hazan, H Lee, K Singh, C Zhang, Y Zhang
arXiv preprint arXiv:1802.03981, 2018
Explaining landscape connectivity of low-cost solutions for multilayer nets
R Kuditipudi, X Wang, H Lee, Y Zhang, Z Li, W Hu, S Arora, R Ge
arXiv preprint arXiv:1906.06247, 2019
Beyond log-concavity: Provable guarantees for sampling multi-modal distributions using simulated tempering langevin monte carlo
R Ge, H Lee, A Risteski
arXiv preprint arXiv:1710.02736, 2017
Towards provable control for unknown linear dynamical systems
S Arora, E Hazan, H Lee, K Singh, C Zhang, Y Zhang
Simulated tempering Langevin Monte Carlo II: An improved proof using soft Markov chain decomposition
R Ge, H Lee, A Risteski
arXiv preprint arXiv:1812.00793, 2018
Pixie: a social chatbot
O Adewale, A Beatson, D Buniatyan, J Ge, M Khodak, H Lee, N Prasad, ...
Alexa prize proceedings, 2017
No-regret prediction in marginally stable systems
U Ghai, H Lee, K Singh, C Zhang, Y Zhang
COLT 2020 - The 33rd Annual Conference on Learning Theory, July 9-12, 2020., 2020
l-adic properties of partition functions
E Belmont, H Lee, A Musat, S Trebat-Leder
arXiv preprint arXiv:1510.01202, 2015
Estimating normalizing constants for log-concave distributions: Algorithms and lower bounds
R Ge, H Lee, J Lu
Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing …, 2020
Robust guarantees for learning an autoregressive filter
H Lee, C Zhang
Algorithmic Learning Theory, 490-517, 2020
Online sampling from log-concave distributions
H Lee, O Mangoubi, NK Vishnoi
arXiv preprint arXiv:1902.08179, 2019
Improved rates for identification of partially observed linear dynamical systems
H Lee
arXiv preprint arXiv:2011.10006, 2020
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows
H Lee, C Pabbaraju, A Sevekari, A Risteski
arXiv preprint arXiv:2107.02951, 2021
Universal Approximation using Well-conditioned Normalizing Flows
H Lee, C Pabbaraju, AP Sevekari, A Risteski
ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit …, 2021
Efficient sampling from the Bingham distribution
R Ge, H Lee, J Lu, A Risteski
Algorithmic Learning Theory, 673-685, 2021
MCMC algorithms for sampling from multimodal and changing distributions
H Lee
Princeton University, 2019
Quadratic polynomials of small modulus cannot represent OR
H Lee
arXiv preprint arXiv:1509.08896, 2015
The system can't perform the operation now. Try again later.
Articles 1–18