Analysis of Dropout in Online Learning

TL;DR

This paper investigates the impact of dropout regularization in online learning, revealing that dropout improves convergence speed by avoiding singular points, which was previously not well understood.

Contribution

It provides the first detailed analysis of dropout's effect on convergence in online learning, demonstrating its effectiveness in this context.

Findings

Dropout improves convergence speed in online learning.

Dropout helps avoid singular points during training.

Dropout is effective as a regularization tool in online learning.

Abstract

Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition. This learning uses a large number of layers and a huge number of units and connections. Therefore, overfitting is a serious problem with it, and the dropout which is a kind of regularization tool is used. However, in online learning, the effect of dropout is not well known. This paper presents our investigation on the effect of dropout in online learning. We analyzed the effect of dropout on convergence speed near the singular point. Our results indicated that dropout is effective in online learning. Dropout tends to avoid the singular point for convergence speed near that point.