Effective Dimension of Exp-concave Optimization
arXiv: Learning, Volume abs/1805.08268, 2018.
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
PPT (Upload PPT)