Optimal Sketching Bounds for Exp concave Stochastic Minimization
arXiv preprint arXiv:1805.08268, 2018.
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
Full Text (Upload PDF)
PPT (Upload PPT)