A Smoothing Stochastic Gradient Method for Composite Optimization

Details A Smoothing Stochastic Gradient Method for Composite Optimization A Smoothing Stochastic Gradient Method for Composite Optimization

2010-08-31

arxiv.org/abs/1008.5204v2

Mathematics

Optimization and Control

working paper

Scientific paper

We consider the unconstrained optimization problem whose objective function is composed of a smooth and a non-smooth conponents where the smooth component is the expectation a random function. This type of problem arises in some interesting applications in machine learning. We propose a stochastic gradient descent algorithm for this class of optimization problem. When the non-smooth component has a particular structure, we propose another stochastic gradient descent algorithm by incorporating a smoothing method into our first algorithm. The proofs of the convergence rates of these two algorithms are given and we show the numerical performance of our algorithm by applying them to regularized linear regression problems with different sets of synthetic data.

Affiliated with

Also associated with

No associations

Rating

A Smoothing Stochastic Gradient Method for Composite Optimization 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 A Smoothing Stochastic Gradient Method for Composite Optimization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Smoothing Stochastic Gradient Method for Composite Optimization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-179422