The proximal distance algorithm

MaRDI QIDQ4588998zbMATH OpenFDO

Authors Kevin L. Keys, Kenneth Lange

Publication date 6 November 2017

Full work available at URL https://arxiv.org/abs/1507.07598

zbMATH Keywords

computational statisticsconvexitymajorizationexact penalty method

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Approximation methods and heuristics in mathematical programming (90C59)

Abstract: The MM principle is a device for creating optimization algorithms satisfying the ascent or descent property. The current survey emphasizes the role of the MM principle in nonlinear programming. For smooth functions, one can construct an adaptive interior point method based on scaled Bregmann barriers. This algorithm does not follow the central path. For convex programming subject to nonsmooth constraints, one can combine an exact penalty method with distance majorization to create versatile algorithms that are effective even in discrete optimization. These proximal distance algorithms are highly modular and reduce to set projections and proximal mappings, both very well-understood techniques in optimization. We illustrate the possibilities in linear programming, binary piecewise-linear programming, nonnegative quadratic programming, $el{l}_0$ regression, matrix completion, and inverse sparse covariance estimation.

Recommendations

• Proximal distance algorithms: theory and practice
• MM optimization algorithms
• Distance majorization and its applications
• Majorization-minimization algorithms for nonsmoothly penalized objective functions
• Proximal algorithms in statistics and machine learning

Cited in

(9)

• Adaptive Convex Clustering of Generalized Linear Models With Application in Purchase Likelihood Prediction
• MM optimization algorithms
• Proximate point searching
• Proximal distance algorithms: theory and practice
• An algorithm for the computation of the Hutchinson distance
• Finding best approximation pairs for two intersections of closed convex sets
• An assembly and decomposition approach for constructing separable minorizing functions in a class of MM algorithms
• A proximal algorithm with quasi distance. Application to habit's formation
• Distance majorization and its applications

This page was built for publication: The proximal distance algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4588998)