Talks
Fall 2017
![](https://old.simons.berkeley.edu/sites/default/files/styles/workshop_main/public/opt7large-01.png?itok=MmjWP0n3)
Natasha 2: Faster Non-convex Optimization Than SGD
Friday, October 6th, 2017, 11:30 am–12:15 pm
Speaker:
We design a stochastic algorithm to train any smooth neural network to eps-approximate local minima, using O(e^{-3.25}) backpropagations. The best result was essentially O(e^{-4}) by SGD.
More broadly, it finds eps-approximate local minima of any smooth nonconvex function in rate O(e^{-3.25}), with only oracle access to stochastic gradients and Hessian-vector products.