Gradient Methods for Stochastic Optimization in Relative Scale
Preprint
Abstract
We propose a new concept of a relatively inexact stochastic subgradient and present novel first-order methods that can use such objects to approximately solve convex optimization problems in relative scale. An important example where relatively inexact subgradients naturally arise is given by the Power or Lanczos algorithms for computing an approximate leading eigenvector of a symmetric positive semidefinite matrix. Using these algorithms as subroutines in our methods, we get new optimization schemes that can provably solve certain large-scale Semidefinite Programming problems with relative accuracy guarantees by using only matrix-vector products.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- Primal-dual subgradient methods for convex problemsMathematical Programming, 2007
- Interior-Point Polynomial Algorithms in Convex Programming1994
- Estimating the Largest Eigenvalue by the Power and Lanczos Algorithms with a Random StartSIAM Journal on Matrix Analysis and Applications, 1992