  


On the von Neumann and FrankWolfe Algorithms with Away Steps
Javier Pena (jfpandrew.cmu.edu) Abstract: The von Neumann algorithm is a simple coordinatedescent algorithm to determine whether the origin belongs to a polytope generated by a finite set of points. When the origin is in the interior of the polytope, the algorithm generates a sequence of points in the polytope that converges linearly to zero. The algorithm's rate of convergence depends on the radius of the largest ball around the origin contained in the polytope. We show that under the weaker condition that the origin is in the polytope, possibly on its boundary, a variant of the von Neumann algorithm that includes generates a sequence of points in the polytope that converges linearly to zero. The new algorithm's rate of convergence depends on a certain geometric parameter of the polytope that extends the above radius but is always positive. Our linear convergence result and geometric insights also extend to a variant of the FrankWolfe algorithm with away steps for minimizing a strongly convex function over a polytope. Keywords: Von Neumann, FrankWolfe, Away Steps, Linear Convergence, Coordinate Descent Category 1: Convex and Nonsmooth Optimization (Convex Optimization ) Category 2: Convex and Nonsmooth Optimization (Nonsmooth Optimization ) Citation: Technical Report, Tepper School, Carnegie Mellon University Download: [PDF] Entry Submitted: 07/14/2015 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  