Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 4 of 4 for “"Mirror prox"”.
-
Saddle point techniques in convex composite and error-in-measurement optimization
… novel composite versions of the state-of-the-art Mirror Descent and Mirror Prox algorithms aimed at solving such type of problems. We demonstrate that the algorithms inherit the favorable efficiency estimate of their prototypes when solving structured variational inequalities. Moreover, we develop …
-
Convergence in min-max optimization
… compared to first-order methods such as Mirror Prox.
-
Algorithm Design and Analysis for Large-Scale Semidefinite Programming and Nonlinear Programming
… well-structured sparse SDPs via a saddle point mirror-prox algorithm with ${cal O}(epsilon^{-1})$ efficiency was developed based on exploiting sparsity structure and reformulating SDPs into smooth convex-concave saddle point problems. An iterative solver-based long-step primal-dual infeasible …
-
Generalized implicit online convex optimization
… A classic way to design OCO algorithm is to approximate the original convex losses with linear models, reducing the OCO problem into an online linear optimization (OLO) problem. Then we only need to solve the OLO problem. However, due to the linearization, the algorithm sacrifices useful …