SoftServe: A Scalable Quasi-Newton Method for Deep Learning | Hacker News - But Better

SoftServe: A Scalable Quasi-Newton Method for Deep Learning arxiv.org

Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization. Two obstacles have limited their use in deep learning: non-convexity and enormous parameter…

1 points•E-Reverance•about 3 hours ago•0 comments•

#deep #newton #quasi #deep learning #quasi newton #softserve #method #scalable

0 comments

No comments yet.

Related stories

A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorchgithub.com
Lobsters · 2 points · over 7 years ago
A Scalable, Formal Method for Design and Automatic Checking of User Interfaces (2001)home.deib.polimi.it
Lobsters · 4 points · over 8 years ago
Deep Learning for Programmers New Release 0.4.0aiprobook.com
Lobsters · 1 points · over 7 years ago
A Brief Perspective on Deep Learning Using Common Lispyoutube.com
Lobsters · 1 points · 7 days ago
“Logic Check” — Fixing Communication Through Deep Learningfixingtao.com
Lobsters · 2 points · about 11 years ago
Using Deep Learning to Create Professional-Level Photographsresearch.googleblog.com
Lobsters · 2 points · about 9 years ago