An inexact regularized proximal Newton method for nonconvex and nonsmooth optimization
Preprint
Abstract
This paper focuses on the minimization of a sum of a twice continuously differentiable function $f$ and a nonsmooth convex function. An inexact regularized proximal Newton method is proposed by an approximation to the Hessian of $f$ involving the $\varrho$th power of the KKT residual. For $\varrho=0$, we justify the global convergence of the iterate sequence for the KL objective function and its R-linear convergence rate for the KL objective function of exponent $1/2$. For $\varrho\in(0,1)$, by assuming that cluster points satisfy a locally H\"{o}lderian error bound of order $q$ on a second-order stationary point set and a local error bound of order $q>1\!+\!\varrho$ on the common stationary point set, respectively, we establish the global convergence of the iterate sequence and its superlinear convergence rate with order depending on $q$ and $\varrho$. A dual semismooth Newton augmented Lagrangian method is also developed for seeking an inexact minimizer of subproblems. Numerical comparisons with two state-of-the-art methods on $\ell_1$-regularized Student's $t$-regressions, group penalized Student's $t$-regressions, and nonconvex image restoration confirm the efficiency of the proposed method.
Keywords
All Related Versions
This publication has 42 references indexed in Scilit:
- Inexact proximal Newton methods for self-concordant functionsMathematical Methods of Operations Research, 2016
- Robust inversion, dimensionality reduction, and randomized samplingMathematical Programming, 2012
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward–backward splitting, and regularized Gauss–Seidel methodsMathematical Programming, 2011
- Convergence Properties of the Regularized Newton Method for the Unconstrained Nonconvex OptimizationApplied Mathematics & Optimization, 2009
- A coordinate gradient descent method for nonsmooth separable minimizationMathematical Programming, 2007
- Tame functions are semismoothMathematical Programming, 2007
- Error bounds for systems of lower semicontinuous functions in Asplund spacesMathematical Programming, 2007
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic featuresMathematical Programming, 2007
- Error bounds and convergence analysis of feasible descent methods: a general approachAnnals of Operations Research, 1993
- A nonsmooth version of Newton's methodMathematical Programming, 1993