Proximal gradient methods for learning: Difference between revisions

Revision as of 12:13, 16 May 2018

Revision as of 05:15, 23 May 2018

Line 84:

== Practical considerations ==

There have been numerous developments within the past decade in [[convex optimization]] techniques which have influenced the application of proximal gradient methods in statistical learning theory. Here we survey a few important topics which can greatly improve practical algorithmic performance of these methods.<ref name=structSparse /><ref name=bach>{{cite journal|last=Bach|first=F.|author2=Jenatton, R. |author3=Mairal, J. |author4=Obozinski, Gl. |title=Optimization with sparsity-inducing penalties|journal=Found. & Trends Mach. Learn.|year=2011|volume=4|issue=1|pages=1–106|doi=10.1561/2200000015|arxiv=1108.0775}}</ref>

=== Adaptive step size ===