Generalized conditional gradient: analysis of convergence and applications

10/22/2015

∙

The objectives of this technical report is to provide additional results on the generalized conditional gradient methods introduced by Bredies et al. [BLM05]. Indeed , when the objective function is smooth, we provide a novel certificate of optimality and we show that the algorithm has a linear convergence rate. Applications of this algorithm are also discussed.

READ FULL TEXT

Generalized conditional gradient: analysis of convergence and applications

Convergence Revisit on Generalized Symmetric ADMM

Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimization

Conditional generalized quantiles based on expected utility model and equivalent characterization of properties

Tight bounds on the convergence rate of generalized ratio consensus algorithms

Remarks on some conditional generalized Borel-Cantelli lemmas

Online Adaptive Methods, Universality and Acceleration

Alternating Projections for Learning with Expectation Constraints

Generalized conditional gradient: analysis of convergence and applications

Related Research

Convergence Revisit on Generalized Symmetric ADMM

Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimization

Conditional generalized quantiles based on expected utility model and equivalent characterization of properties

Tight bounds on the convergence rate of generalized ratio consensus algorithms

Remarks on some conditional generalized Borel-Cantelli lemmas

Online Adaptive Methods, Universality and Acceleration

Alternating Projections for Learning with Expectation Constraints