  


Generalized Conditional Gradient with Augmented Lagrangian for Composite Minimization
Antonio SilvetiFalls (tonys.fallsgmail.com) Abstract: In this paper we propose a splitting scheme which hybridizes generalized conditional gradient with a proximal step which we call CGALP algorithm, for minimizing the sum of three proper convex and lowersemicontinuous functions in real Hilbert spaces. The minimization is subject to an affine constraint, that allows in particular to deal with composite problems (sum of more than three functions) in a separate way by the usual product space technique. While classical conditional gradient methods require Lipschitzcontinuity of the gradient of the differentiable part of the objective, CGALP needs only differentiability (on an appropriate subset), hence circumventing the intricate question of Lipschitz continuity of gradients. For the two remaining functions in the objective, we do not require any additional regularity assumption. The second function, possibly nonsmooth, is assumed simple, i.e., the associated proximal mapping is easily computable. For the third function, again nonsmooth, we just assume that its domain is weakly compact and that a linearly perturbed minimization oracle is accessible. In particular, this last function can be chosen to be the indicator of a nonempty bounded closed convex set, in order to deal with additional constraints. Finally, the affine constraint is addressed by the augmented Lagrangian approach. Our analysis is carried out for a wide choice of algorithm parameters satisfying so called "open loop" rules. As main results, under mild conditions, we show asymptotic feasibility with respect to the affine constraint, boundedness of the dual multipliers, and convergence of the Lagrangian values to the saddlepoint optimal value. We also provide (subsequential) rates of convergence for both the feasibility gap and the Lagrangian values. Keywords: Conditional gradient; Augmented Lagrangian; Composite minimization; Proximal mapping; Moreau envelope. Category 1: Convex and Nonsmooth Optimization Category 2: Nonlinear Optimization Category 3: Infinite Dimensional Optimization Citation: Campus 2, Sciences 3, 6 Boulevard du Maréchal Juin, 14000 Caen, France January, 2019 Download: [PDF] Entry Submitted: 01/04/2019 Modify/Update this entry  
Visitors  Authors  More about us  Links  
Subscribe, Unsubscribe Digest Archive Search, Browse the Repository

Submit Update Policies 
Coordinator's Board Classification Scheme Credits Give us feedback 
Optimization Journals, Sites, Societies  