Provable training of a ReLU gate with an iterative non-gradient algorithm

In this work, we demonstrate provable guarantees on the training of a single ReLU gate in hitherto unexplored regimes. We give a simple iterative stochastic algorithm that can train a ReLU gate in the realizable setting in linear time while using significantly milder conditions on the data distribut...

Celý popis

Podrobná bibliografia

Vydané v:	Neural networks Ročník 151; s. 264 - 275
Hlavní autori:	Karmakar, Sayar, Mukherjee, Anirbit
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Elsevier Ltd 01.07.2022
Predmet:	Neural nets Non-gradient iterative algorithms Non-smooth non-convex optimization Stochastic algorithms Stochastic algorithms Non-smooth non-convex optimization Neural nets Non-gradient iterative algorithms
ISSN:	0893-6080, 1879-2782, 1879-2782
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!