Natasha 2: Faster Non-Convex Optimization Than SGD
Abstract
We design a stochastic algorithm to find ε-approximate local minima of any smooth nonconvex function in rate with only oracle access to stochastic gradients. The best result before this work was by stochastic gradient descent (SGD).
上一篇:Large-Scale Stochastic Sampling from the Probability Simplex
下一篇:Inferring Latent Velocities from Weather Radar Data using Gaussian Processes
还没有评论,说两句吧!
热门资源
The Variational S...
Unlike traditional images which do not offer in...
Learning to Predi...
Much of model-based reinforcement learning invo...
Stratified Strate...
In this paper we introduce Stratified Strategy ...
Learning to learn...
The move from hand-designed features to learned...
A Mathematical Mo...
Direct democracy, where each voter casts one vo...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com