Follow
Ji Xu
Ji Xu
Verified email at columbia.edu - Homepage
Title
Cited by
Cited by
Year
Two models of double descent for weak features
M Belkin, D Hsu, J Xu
SIAM Journal on Mathematics of Data Science 2 (4), 1167-1180, 2020
3962020
Global analysis of expectation maximization for mixtures of two gaussians
J Xu, DJ Hsu, A Maleki
Advances in Neural Information Processing Systems 29, 2016
1472016
On the Optimal Weighted Regularization in Overparameterized Linear Regression
D Wu, J Xu
Advances in Neural Information Processing Systems 33, 10112-10123, 2020
1282020
Optimization-Based AMP for Phase Retrieval: The Impact of Initialization and Regularization
J Ma, J Xu, A Maleki
IEEE Transactions on Information Theory 65 (6), 3600-3629, 2019
702019
On the number of variables to use in principal component regression
J Xu, DJ Hsu
Advances in neural information processing systems 32, 2019
372019
When does preconditioning help or hurt generalization?
S Amari, J Ba, R Grosse, X Li, A Nitanda, T Suzuki, D Wu, J Xu
arXiv preprint arXiv:2006.10732, 2020
362020
On the proliferation of support vectors in high dimensions
D Hsu, V Muthukumar, J Xu
International Conference on Artificial Intelligence and Statistics, 91-99, 2021
332021
Benefits of over-parameterization with EM
J Xu, DJ Hsu, A Maleki
Advances in Neural Information Processing Systems 31, 2018
322018
Spectral method for phase retrieval: an expectation propagation perspective
J Ma, R Dudeja, J Xu, A Maleki, X Wang
IEEE Transactions on Information Theory 67 (2), 1332-1355, 2021
212021
Consistent risk estimation in high-dimensional linear regression
J Xu, A Maleki, KR Rad, D Hsu
arXiv preprint arXiv:1902.01753 864, 2019
202019
Approximate message passing for amplitude based optimization
J Ma, J Xu, A Maleki
International Conference on Machine Learning, 3365-3374, 2018
132018
Analysis of sensing spectral for signal recovery under a generalized linear model
J Ma, J Xu, A Maleki
Advances in Neural Information Processing Systems 34, 22601-22613, 2021
122021
Consistent risk estimation in moderately high-dimensional linear regression
J Xu, A Maleki, KR Rad, D Hsu
IEEE Transactions on Information Theory 67 (9), 5997-6030, 2021
112021
How many variables should be entered in a principal component regression equation
J Xu, D Hsu
arXiv preprint arXiv:1906.01139, 2019
82019
Impact of the sensing spectrum on signal recovery in generalized linear models
J Ma, J Xu, A Maleki
arXiv preprint arXiv:2111.03237, 2021
22021
Towards Designing Optimal Sensing Matrices for Generalized Linear Inverse Problems
J Ma, J Xu, A Maleki
IEEE Transactions on Information Theory, 2023
2023
A Geometric Approach to Dynamical System: Global Analysis for Non-Convex Optimization
J Xu
Columbia University, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–17