Search Results for author:
Found 6 papers, 2 papers with code
Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers
We present a new, stochastic variant of the projective splitting (PS) family of algorithms for monotone inclusion problems.
Single-Forward-Step Projective Splitting: Exploiting Cocoercivity
In the convex optimization context, cocoercivity is equivalent to Lipschitz differentiability.
Projective Splitting with Forward Steps only Requires Continuity
A recent innovation in projective splitting algorithms for monotone operator inclusions has been the development of a procedure using two forward steps instead of the customary proximal steps for operators that are Lipschitz continuous.
Convergence Rates for Projective Splitting
Second, for strongly monotone inclusions, strong convergence is established as well as an ergodic $O(1/\sqrt{k})$ convergence rate for the distance of the iterates to the solution.
Projective Splitting with Forward Steps: Asynchronous and Block-Iterative Operator Splitting
Forward steps can be used for any Lipschitz-continuous operators provided the stepsize is bounded by the inverse of the Lipschitz constant.
Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement
We describe a learning procedure enhancing L1-penalized regression by adding dynamically generated rules describing multidimensional “box” sets.
