Revisiting Projection-Free Optimization for Strongly Convex Constraint Sets
نویسندگان
چکیده
منابع مشابه
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
We provide stronger and more general primal-dual convergence results for FrankWolfe-type algorithms (a.k.a. conditional gradient) for constrained convex optimization, enabled by a simple framework of duality gap certificates. Our analysis also holds if the linear subproblems are only solved approximately (as well as if the gradients are inexact), and is proven to be worst-case optimal in the sp...
متن کاملIncremental Constraint Projection-Proximal Methods for Nonsmooth Convex Optimization
We consider convex optimization problems with structures that are suitable for stochastic sampling. In particular, we focus on problems where the objective function is an expected value or is a sum of a large number of component functions, and the constraint set is the intersection of a large number of simpler sets. We propose an algorithmic framework for projection-proximal methods using rando...
متن کاملFaster Projection-free Convex Optimization over the Spectrahedron
Minimizing a convex function over the spectrahedron, i.e., the set of all d ⇥ d positive semidefinite matrices with unit trace, is an important optimization task with many applications in optimization, machine learning, and signal processing. It is also notoriously difficult to solve in large-scale since standard techniques require to compute expensive matrix decompositions. An alternative is t...
متن کاملDistributed Optimization for Non-Strongly Convex Regularizers
We develop primal-dual algorithms for distributed training of linear models in the Spark framework. We present the ProxCoCoA+ method which represents a generalization of the CoCoA+ algorithm and extends it to the case of general strongly convex regularizers. A primal-dual convergence rate analysis is provided along with an experimental evaluation of the algorithm on the problem of elastic net r...
متن کاملConvex Optimization without Projection Steps
We study the general problem of minimizing a convex function over a compact convex domain. We will investigate a simple iterative approximation algorithm based on the method by Frank & Wolfe [FW56], that does not need projection steps in order to stay inside the optimization domain. Instead of a projection step, the linearized problem defined by a current subgradient is solved, which gives a st...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33011576