Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent

Details Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent

2011-07-13

arxiv.org/abs/1107.2490v2

Computer Science

Learning

Scientific paper

For large scale learning problems, it is desirable if we can obtain the optimal model parameters by going through the data in only one pass. Polyak and Juditsky (1992) showed that asymptotically the test performance of the simple average of the parameters obtained by stochastic gradient descent (SGD) is as good as that of the parameters which minimize the empirical cost. However, to our knowledge, despite its optimal asymptotic convergence rate, averaged SGD (ASGD) received little attention in recent research on large scale learning. One possible reason is that it may take a prohibitively large number of training samples for ASGD to reach its asymptotic region for most real problems. In this paper, we present a finite sample analysis for the method of Polyak and Juditsky (1992). Our analysis shows that it indeed usually takes a huge number of samples for ASGD to reach its asymptotic region for improperly chosen learning rate. More importantly, based on our analysis, we propose a simple way to properly set learning rate so that it takes a reasonable amount of data for ASGD to reach its asymptotic region. We compare ASGD using our proposed learning rate with other well known algorithms for training large scale linear classifiers. The experiments clearly show the superiority of ASGD.

Affiliated with

Also associated with

No associations

Rating

Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-165324