MétaCan
← all works

On the importance of initialization and momentum in deep learning

2013· article· en· 3,536 citations· W104184427 on OpenAlex

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Abstract

Deep and recurrent neural networks (DNNs and RNNs respectively) are powerful models that were considered to be almost impossible to train using stochastic gradient descent with momentum. In this paper, we show that when stochastic gradient descent with momentum uses a well-designed random initialization and a particular type of slowly increasing schedule for the momentum parameter, it can train both DNNs and RNNs (on datasets with long-term dependencies) to levels of performance that were previously achievable only with Hessian-Free optimization. We find that both the initialization and the momentum are crucial since poorly initialized networks cannot be trained with momentum and well-initialized networks perform markedly worse when the momentum is absent or poorly tuned. Our success training these models suggests that previous attempts to train deep and recurrent neural networks from random initializations have likely failed due to poor initialization schemes. Furthermore, carefully tuned momentum methods suffice for dealing with the curvature issues in deep and recurrent network training objectives without the need for sophisticated second-order methods. 1.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
Topic
Stochastic Gradient Optimization Techniques
Field
Computer Science
Canadian institutions
University of Toronto
Funders
Keywords
InitializationMomentum (technical analysis)Computer scienceRecurrent neural networkGradient descentStochastic gradient descentDeep learningArtificial intelligenceDeep neural networksArtificial neural networkScheduleMachine learningMathematical optimizationAlgorithmMathematics
Has abstract in OpenAlex
yes