Statistical Learning
NEON2: Finding Local Minima via First-Order Oracles
It works both in the stochastic and the deterministic settings, without hurting the algorithm'sperformance. As applications, our reduction turns Natasha2 into a first-order method without hurting its theoretical performance. It also converts SGD, GD, SCSG, and SVRG into algorithms finding approximate local minima, outperforming some bestknownresults.