Wotao Yin, University of California, Los Angeles


Convergence Rates of Operator Splitting Methods


Splitting schemes are a class of powerful algorithms that solve complicated monotone inclusions and convex optimization problems that are built from many simpler pieces. They give rise to algorithms in which the simple pieces of the decomposition are processed individually. This leads to easily implementable and highly parallelizable algorithms, which often obtain nearly state-of-the-art performance.

This talk overviews the convergence rates of several general splitting algorithms and provide examples. In some cases, we prove the tightness of our results.


Damek Davis (UCLA)

« Back