Optimal Sketching Bounds for Exp concave Stochastic Minimization

Naman Agarwal
Naman Agarwal

arXiv preprint arXiv:1805.08268, 2018.

Cited by: 0|Bibtex|Views5|Links

Abstract:

We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension. For common eigendecay patterns of the population covariance matrix, this quantity is significantly smaller than the ambient dimension. Our results reveal interesting connections to sketching result...More

Code:

Data:

Your rating :
0

 

Tags
Comments