NIPS Proceedingsβ

Chi Jin

4 Papers

  • Gradient Descent Can Take Exponential Time to Escape Saddle Points (2017)
  • Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences (2016)
  • Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent (2016)
  • Dimensionality Dependent PAC-Bayes Margin Bound (2012)