Toward theoretical understanding of deep learning Sanjeev Arora Optimization Ge, Huang, Jin, Yuan COLT 2015. "Evading saddle points: online stochastic gradient descent for tensor decomposition." Jin, Ge, Netrapalli, Kakade, Jordan ICML'17. How to escape saddle points efficiently. Blog post. 2nd order black box methods for deep learning. Paper 1 by Agrarwal et al and Paper 2 by Carmon et al. Blog
{{#tags}}- {{label}}
{{/tags}}