Effective Dimension of Exp-concave Optimization

Naman Agarwal
Naman Agarwal

arXiv: Learning, Volume abs/1805.08268, 2018.

Cited by: 0|Bibtex|Views7|Links
EI

Abstract:

We investigate the role of the effective dimension $d_lambda$ in determining both the statistical and the computational costs associated with exp-concave stochastic minimization. main statistical result is a nearly tight bound of order $d_lambda/epsilon$ on the sample complexity of any algorithm that approximately minimizes the empirical...More

Code:

Data:

Your rating :
0

 

Tags
Comments