Gradient Methods for Stochastic Optimization in Relative Scale
From MaRDI portal
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.
This page was built for publication: Gradient Methods for Stochastic Optimization in Relative Scale
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6423889)
