A1054
Title: Flexible regularized estimating equations: Some new perspectives
Authors: Archer Yang - McGill University (Canada) [presenting]
Abstract: Some observations are made about the equivalences between regularized estimating equations, fixed-point problems and variational inequalities: (a)A regularized estimating equation is equivalent to a fixed-point problem, specified via the proximal operator of the corresponding penalty. (b) A regularized estimating equation is equivalent to a (generalized) variational quality. Both equivalences extend to any estimating equations with convex penalty functions. To solve large-scale regularized estimating equations, it is worth pursuing computation by exploiting these connections. While fast computational algorithms are less developed for regularized estimating equations, many efficient solvers exist for fixed-point problems and variational inequalities. In this regard, some efficient and scalable solvers which can deliver a hundred-fold speed improvement are applied. These connections can lead to further research in both computational and theoretical aspects of the regularized estimating equations.
