Tight Lower Bounds for Multiplicative Weights Algorithmic Families

ICALP, 2017.

Cited by: 3|Bibtex|Views5|Links
EI

Abstract:

We study the fundamental problem of prediction with expert advice and develop regret lower bounds for a large family of algorithms for this problem. We develop simple adversarial primitives, that lend themselves to various combinations leading to sharp lower bounds for many algorithmic families. We use these primitives to show that the cl...More

Code:

Data:

Your rating :
0

 

Tags
Comments