Chi Jin

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

How to Escape Saddle Points Efficiently

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

Gradient Descent Can Take Exponential Time to Escape Saddle Points

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

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

Faster eigenvector computation via shift-and-invert preconditioning

Computing Matrix Squareroot via Non Convex Local Search

Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent

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