Is this you? Create Your Porfile
Avatar

Chi Jin

University of California, Berkeley

Network

Latest external collaboration on country level. Dive into details by clicking on the dots.

Explore More

Hotspot

Dive into the research topics where Chi Jin is active.

Explore More

Publication

Featured researches published by Chi Jin.

conference on learning theory | 2015

Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition

Rong Ge; Furong Huang; Chi Jin; Yang Yuan

international conference on machine learning | 2017

How to Escape Saddle Points Efficiently

Chi Jin; Rong Ge; Praneeth Netrapalli; Sham M. Kakade; Michael I. Jordan

international conference on machine learning | 2017

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis.

Rong Ge; Chi Jin; Yi Zheng

neural information processing systems | 2017

Gradient Descent Can Take Exponential Time to Escape Saddle Points

Simon S. Du; Chi Jin; Jason D. Lee; Michael I. Jordan; Aarti Singh; Barnabás Póczos

arXiv: Data Structures and Algorithms | 2015

Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation

Chi Jin; Sham M. Kakade; Cameron Musco; Praneeth Netrapalli; Aaron Sidford

conference on learning theory | 2016

Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm

Prateek Jain; Chi Jin; Sham M. Kakade; Praneeth Netrapalli; Aaron Sidford

international conference on machine learning | 2016

Faster eigenvector computation via shift-and-invert preconditioning

Dan Garber; Elad Hazan; Chi Jin; Sham M. Kakade; Cameron Musco; Praneeth Netrapalli; Aaron Sidford

arXiv: Numerical Analysis | 2015

Computing Matrix Squareroot via Non Convex Local Search

Prateek Jain; Chi Jin; Sham M. Kakade; Praneeth Netrapalli

conference on learning theory | 2018

Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent

Chi Jin; Praneeth Netrapalli; Michael I. Jordan

neural information processing systems | 2016

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent

Chi Jin; Sham M. Kakade; Praneeth Netrapalli

Explore More

Collaboration

Dive into the Chi Jin's collaboration.

Top Co-Authors
Avatar

Praneeth Netrapalli

Microsoft

View shared research outputs
Top Co-Authors
Avatar

Sham M. Kakade

University of Washington

View shared research outputs
Top Co-Authors
Avatar

Michael I. Jordan

University of California

View shared research outputs
Top Co-Authors
Avatar

Rong Ge

Duke University

View shared research outputs
Top Co-Authors
Avatar

Aaron Sidford

Stanford University

View shared research outputs
Top Co-Authors
Avatar

Prateek Jain

Microsoft

View shared research outputs
Top Co-Authors
Avatar

Liwei Wang

Peking University

View shared research outputs
Top Co-Authors
Avatar

Cameron Musco

Massachusetts Institute of Technology

View shared research outputs
Top Co-Authors
Avatar

Lydia T. Liu

University of California

View shared research outputs
Top Co-Authors
Avatar

Junliang Huang

Peking University

View shared research outputs
Explore More
Researchain Logo
Decentralizing Knowledge