Timezone: »

RECAPP: Crafting a More Efficient Catalyst for Convex Optimization
Yair Carmon · Arun Jambulapati · Yujia Jin · Aaron Sidford

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #714

The accelerated proximal point method (APPA), also known as "Catalyst", is a well-established reduction from convex optimization to approximate proximal point computation (i.e., regularized minimization). This reduction is conceptually elegant and yields strong convergence rate guarantees. However, these rates feature an extraneous logarithmic term arising from the need to compute each proximal point to high accuracy. In this work, we propose a novel Relaxed Error Criterion for Accelerated Proximal Point (RECAPP) that eliminates the need for high accuracy subproblem solutions. We apply RECAPP to two canonical problems: finite-sum and max-structured minimization. For finite-sum problems, we match the best known complexity, previously obtained by carefully-designed problem-specific algorithms. For minimizing max_y f(x,y) where f is convex in x and strongly-concave in y, we improve on the best known (Catalyst-based) bound by a logarithmic factor.

Author Information

Yair Carmon (Tel Aviv University)
Arun Jambulapati (Stanford)
Yujia Jin (Stanford University)
Aaron Sidford (Stanford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors