Perspective Maximum Likelihood-Type Estimation via Proximal Decomposition

TL;DR

This paper presents a unified optimization framework called perspective M-estimation that generalizes many statistical models and enables efficient, convergent algorithms through proximal splitting techniques.

Contribution

It introduces perspective M-estimation, a novel model that unifies various statistical estimators using perspective functions and develops new proximal algorithms for them.

Findings

Broad applicability demonstrated on synthetic and real data.

Convergent algorithms derived via proximal splitting.

Unification of multiple estimators under a single framework.

Abstract

We introduce an optimization model for maximum likelihood-type estimation (M-estimation) that generalizes a large class of existing statistical models, including Huber's concomitant M-estimator, Owen's Huber/Berhu concomitant estimator, the scaled lasso, support vector machine regression, and penalized estimation with structured sparsity. The model, termed perspective M-estimation, leverages the observation that convex M-estimators with concomitant scale as well as various regularizers are instances of perspective functions. Such functions are amenable to proximal analysis, which leads to principled and provably convergent optimization algorithms via proximal splitting. Using a geometrical approach based on duality, we derive novel proximity operators for several perspective functions of interest. Numerical experiments on synthetic and real-world data illustrate the broad applicability of the proposed framework.