Jason D. Lee
Jason D. Lee
Associate Professor of Electrical Engineering and Computer Science, Princeton University
Bestätigte E-Mail-Adresse bei - Startseite
Zitiert von
Zitiert von
Gradient descent finds global minima of deep neural networks
SS Du, JD Lee, H Li, L Wang, X Zhai
arXiv preprint arXiv:1811.03804, 2018
Exact post-selection inference, with application to the lasso
JD Lee, DL Sun, Y Sun, JE Taylor
The Annals of Statistics 44 (3), 907-927, 2016
Gradient descent only converges to minimizers
JD Lee, M Simchowitz, MI Jordan, B Recht
Conference on learning theory, 1246-1257, 2016
On the theory of policy gradient methods: Optimality, approximation, and distribution shift
A Agarwal, SM Kakade, JD Lee, G Mahajan
Journal of Machine Learning Research 22 (98), 1-76, 2021
Matrix completion has no spurious local minimum
R Ge, JD Lee, T Ma
Advances in neural information processing systems 29, 2016
Matrix completion and low-rank SVD via fast alternating least squares
T Hastie, R Mazumder, J Lee, R Zadeh
Journal of Machine Learning Research, 2014
A kernelized Stein discrepancy for goodness-of-fit tests
Q Liu, J Lee, M Jordan
International conference on machine learning, 276-284, 2016
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks
M Soltanolkotabi, A Javanmard, JD Lee
IEEE Transactions on Information Theory 65 (2), 742-769, 2018
Proximal Newton-type methods for minimizing composite functions
JD Lee, Y Sun, MA Saunders
SIAM Journal on Optimization 24 (3), 1420-1443, 2014
Communication-efficient distributed statistical inference
MI Jordan, JD Lee, Y Yang
Journal of the American Statistical Association, 2019
Characterizing implicit bias in terms of optimization geometry
S Gunasekar, J Lee, D Soudry, N Srebro
International Conference on Machine Learning, 1832-1841, 2018
Implicit bias of gradient descent on linear convolutional networks
S Gunasekar, JD Lee, D Soudry, N Srebro
Advances in neural information processing systems 31, 2018
Solving a class of non-convex min-max games using iterative first order methods
M Nouiehed, M Sanjabi, T Huang, JD Lee, M Razaviyayn
Advances in Neural Information Processing Systems 32, 2019
Kernel and rich regimes in overparametrized models
B Woodworth, S Gunasekar, JD Lee, E Moroshko, P Savarese, I Golan, ...
Conference on Learning Theory, 3635-3673, 2020
First-order methods almost always avoid strict saddle points
JD Lee, I Panageas, G Piliouras, M Simchowitz, MI Jordan, B Recht
Mathematical programming 176 (1-2), 311-337, 2019
Learning one-hidden-layer neural networks with landscape design
R Ge, JD Lee, T Ma
arXiv preprint arXiv:1711.00501, 2017
Gradient descent can take exponential time to escape saddle points
SS Du, C Jin, JD Lee, MI Jordan, A Singh, B Poczos
Advances in neural information processing systems 30, 2017
On the power of over-parametrization in neural networks with quadratic activation
S Du, J Lee
International conference on machine learning, 1329-1338, 2018
Stochastic subgradient method converges on tame functions
D Davis, D Drusvyatskiy, S Kakade, JD Lee
Foundations of computational mathematics 20 (1), 119-154, 2020
Few-shot learning via learning the representation, provably
SS Du, W Hu, SM Kakade, JD Lee, Q Lei
arXiv preprint arXiv:2002.09434, 2020
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20