Add to ORKGWe propose a conditional gradient framework for a composite convex minimization template with broad applications. Our approach combines the notions of smoothing and homotopy under the CGM framework, and provably achieves the optimal O(1/sqrt(k)) convergence rate. We demonstrate that the same rate holds if the linear subproblems are solved approximately with additive or multiplicative error. Specific applications of the framework include the non-smooth minimization semidefinite programming, minimization with linear inclusion constraints over a compact domain. We provide numerical evidence to demonstrate the benefits of the new framework
International audience<p>We propose a new first-order primal-dual optimization framework for a conve...
The self-concordant-like property of a smooth convex func- tion is a new analytical structure that g...
We propose a stochastic gradient framework for solving stochastic composite convex optimization prob...
International audience<p>We propose a conditional gradient framework for a composite convex minimiza...
We propose a stochastic conditional gradient method (CGM) for minimizing convex finitesum objectives...
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objective...
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objective...
This paper considers a generic convex minimization template with affine constraints over a compact d...
We introduce and analyze an algorithm for the minimization of convex functions that are the sum of d...
International audienceIn this paper we propose a splitting scheme which hybridizes generalized condi...
International audienceIn this paper we propose a splitting scheme which hybridizes generalized condi...
In this paper we propose a splitting scheme which hybridizes generalized conditional gradient with a...
In this paper we propose a splitting scheme which hybridizes generalized conditional gradient with a...
A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), min...
We propose a new and low per-iteration complexity first-order primal-dual optimization framework for...
International audience<p>We propose a new first-order primal-dual optimization framework for a conve...
The self-concordant-like property of a smooth convex func- tion is a new analytical structure that g...
We propose a stochastic gradient framework for solving stochastic composite convex optimization prob...
International audience<p>We propose a conditional gradient framework for a composite convex minimiza...
We propose a stochastic conditional gradient method (CGM) for minimizing convex finitesum objectives...
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objective...
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objective...
This paper considers a generic convex minimization template with affine constraints over a compact d...
We introduce and analyze an algorithm for the minimization of convex functions that are the sum of d...
International audienceIn this paper we propose a splitting scheme which hybridizes generalized condi...
International audienceIn this paper we propose a splitting scheme which hybridizes generalized condi...
In this paper we propose a splitting scheme which hybridizes generalized conditional gradient with a...
In this paper we propose a splitting scheme which hybridizes generalized conditional gradient with a...
A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), min...
We propose a new and low per-iteration complexity first-order primal-dual optimization framework for...
International audience<p>We propose a new first-order primal-dual optimization framework for a conve...
The self-concordant-like property of a smooth convex func- tion is a new analytical structure that g...
We propose a stochastic gradient framework for solving stochastic composite convex optimization prob...