Finding Approximate Local Minima Faster than Gradient Descent

Abstract

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our algorithm to find an approximate local minimum is even faster than that of gradient descent to find a critical point. Our algorithm applies to a general class of optimization problems including training a neural network and other non-convex objectives arising in machine learning.

Cited by in corpus (5)

• On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
• Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
• Second-Order Stochastic Optimization for Machine Learning in Linear Time
• Fast minimization of structured convex quartics
• A Variance Controlled Stochastic Method with Biased Estimation for Faster Non-convex Optimization