Timezone: »

Regularized Nonlinear Acceleration
Damien Scieur · Alexandre d'Aspremont · Francis Bach

Wed Dec 07 07:40 AM -- 08:00 AM (PST) @ Area 3

We describe a convergence acceleration technique for generic optimization problems. Our scheme computes estimates of the optimum from a nonlinear average of the iterates produced by any optimization method. The weights in this average are computed via a simple and small linear system, whose solution can be updated online. This acceleration scheme runs in parallel to the base algorithm, providing improved estimates of the solution on the fly, while the original optimization method is running. Numerical experiments are detailed on classical classification problems.

Author Information

Damien Scieur (INRIA - ENS)
Alexandre d'Aspremont (CNRS - Ecole Normale Supérieure)
Francis Bach (INRIA - Ecole Normale Superieure)

More from the Same Authors