Chi Jin
Chi Jin
Ph.D student, UC Berkeley
Verified email at berkeley.edu - Homepage
TitleCited byYear
Escaping from saddle points—online stochastic gradient for tensor decomposition
R Ge, F Huang, C Jin, Y Yuan
Conference on Learning Theory, 797-842, 2015
5462015
How to escape saddle points efficiently
C Jin, R Ge, P Netrapalli, SM Kakade, MI Jordan
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
2762017
No spurious local minima in nonconvex low rank problems: A unified geometric analysis
R Ge, C Jin, Y Zheng
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
1812017
Accelerated gradient descent escapes saddle points faster than gradient descent
C Jin, P Netrapalli, MI Jordan
arXiv preprint arXiv:1711.10456, 2017
902017
Streaming PCA: Matching matrix Bernstein and near-optimal finite sample guarantees for Oja’s algorithm
P Jain, C Jin, SM Kakade, P Netrapalli, A Sidford
Conference on learning theory, 1147-1164, 2016
82*2016
Faster Eigenvector Computation via Shift-and-Invert Preconditioning.
D Garber, E Hazan, C Jin, SM Kakade, C Musco, P Netrapalli, A Sidford
ICML, 2626-2634, 2016
81*2016
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, 1067-1077, 2017
762017
Is q-learning provably efficient?
C Jin, Z Allen-Zhu, S Bubeck, MI Jordan
Advances in Neural Information Processing Systems, 4863-4873, 2018
592018
Provable efficient online matrix completion via non-convex stochastic gradient descent
C Jin, SM Kakade, P Netrapalli
Advances in Neural Information Processing Systems, 4520-4528, 2016
582016
Stochastic cubic regularization for fast nonconvex optimization
N Tripuraneni, M Stern, C Jin, J Regier, MI Jordan
Advances in neural information processing systems, 2899-2908, 2018
572018
Local maxima in the likelihood of gaussian mixture models: Structural results and algorithmic consequences
C Jin, Y Zhang, S Balakrishnan, MJ Wainwright, MI Jordan
Advances in neural information processing systems, 4116-4124, 2016
512016
Efficient algorithms for large-scale generalized eigenvector computation and canonical correlation analysis
R Ge, C Jin, P Netrapalli, A Sidford
International Conference on Machine Learning, 2741-2750, 2016
372016
Global convergence of non-convex gradient descent for computing matrix squareroot
P Jain, C Jin, SM Kakade, P Netrapalli
arXiv preprint arXiv:1507.05854, 2015
32*2015
Dimensionality dependent PAC-Bayes margin bound
C Jin, L Wang
Advances in neural information processing systems, 1034-1042, 2012
212012
On the local minima of the empirical risk
C Jin, LT Liu, R Ge, MI Jordan
Advances in Neural Information Processing Systems, 4896-4905, 2018
19*2018
Minmax optimization: Stable limit points of gradient descent ascent are locally optimal
C Jin, P Netrapalli, MI Jordan
arXiv preprint arXiv:1902.00618, 2019
162019
Stochastic Gradient Descent Escapes Saddle Points Efficiently
C Jin, P Netrapalli, R Ge, SM Kakade, MI Jordan
arXiv preprint arXiv:1902.04811, 2019
152019
Sampling can be faster than optimization
YA Ma, Y Chen, C Jin, N Flammarion, MI Jordan
arXiv preprint arXiv:1811.08413, 2018
132018
Differentially private data releasing for smooth queries
Z Wang, C Jin, K Fan, J Zhang, J Huang, Y Zhong, L Wang
The Journal of Machine Learning Research 17 (1), 1779-1820, 2016
8*2016
Stability and convergence trade-off of iterative optimization algorithms
Y Chen, C Jin, B Yu
arXiv preprint arXiv:1804.01619, 2018
72018
The system can't perform the operation now. Try again later.
Articles 1–20