Online Learning with Continuous Variations: Dynamic Regret and Reductions

arXiv: Learning, 2019.

Cited by: 7|Bibtex|Views41
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We study the dynamic regret of a new class of online learning problems, in which the gradient of the loss function changes continuously across rounds with respect to the learneru0027s decisions. This setup is motivated by the use of online learning as a tool to analyze the performance of iterative algorithms. Our goal is to identify inter...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments