Timezone: »

Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices
John Duchi · Oliver Hinder · Andrew Naber · Yinyu Ye

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1637

We present an extension of the conditional gradient method to problems whose feasible sets are convex cones. We provide a convergence analysis for the method and for variants with nonconvex objectives, and we extend the analysis to practical cases with effective line search strategies. For the specific case of the positive semidefinite cone, we present a memory-efficient version based on randomized matrix sketches and advocate a heuristic greedy step that greatly improves its practical performance. Numerical results on phase retrieval and matrix completion problems indicate that our method can offer substantial advantages over traditional conditional gradient and Burer-Monteiro approaches.

Author Information

John Duchi (Stanford)
Oliver Hinder (University of Pittsburgh)
Andrew Naber (Stanford University)
Yinyu Ye (Standord)

More from the Same Authors