Proximal quasi-Newton Methods Research Articles

A proximal quasi-Newton method based on memoryless modified symmetric rank-one formula

<p style='text-indent:20px;'>We consider proximal gradient methods for minimizing a composite function of a differentiable function and a convex function. To accelerate the general proximal gradient methods, we focus on proximal quasi-Newton type methods based on proximal mappings scaled by quasi-Newton matrices. Although it is usually difficult to compute the scaled proximal mappings, applying the memoryless symmetric rank-one (SR1) formula makes this easier. Since the scaled (quasi-Newton) matrices must be positive definite, we develop an algorithm using the memoryless SR1 formula based on a modified spectral scaling secant condition. We give the subsequential convergence property of the proposed method for general objective functions. In addition, we show the R-linear convergence property of the method under a strong convexity assumption. Finally, some numerical results are reported.</p>

A Proximal Quasi-Newton Trust-Region Method for Nonsmooth Regularized Optimization

We develop a trust-region method for minimizing the sum of a smooth term (f) and a nonsmooth term (h), both of which can be nonconvex. Each iteration of our method minimizes a possibly nonconvex model of (f + h) in a trust region. The model coincides with (f + h) in value and subdifferential at the center. We establish global convergence to a first-order stationary point when (f) satisfies a smoothness condition that holds, in particular, when it has a Lipschitz-continuous gradient, and (h) is proper and lower semicontinuous. The model of (h) is required to be proper, lower semi-continuous and prox-bounded. Under these weak assumptions, we establish a worst-case (O(1/\epsilon^2)) iteration complexity bound that matches the best known complexity bound of standard trust-region methods for smooth optimization. We detail a special instance, named TR-PG, in which we use a limited-memory quasi-Newton model of (f) and compute a step with the proximal gradient method, resulting in a practical proximal quasi-Newton method. We establish similar convergence properties and complexity bound for a quadratic regularization variant, named R2, and provide an interpretation as a proximal gradient method with adaptive step size for nonconvex problems. R2 may also be used to compute steps inside the trust-region method, resulting in an implementation named TR-R2. We describe our Julia implementations and report numerical results on inverse problems from sparse optimization and signal processing. Both TR-PG and TR-R2 exhibit promising performance and compare favorably with two linesearch proximal quasi-Newton methods based on convex models.

An active-set proximal quasi-Newton algorithm for ℓ1-regularized minimization over a sphere constraint

The -regularized minimization has been widely used in many data science applications, and certain special constrained -regularized minimizations have also been proposed in some recent applications. In this paper, we consider a sphere constrained -regularized minimization, which can arise in image processing, signal recognition and sparse principal component analysis. Viewing the sphere as a simple Riemannian manifold, manifold-based methods for non-smooth minimization can be applied to solve such a problem, but may still encounter slow convergence in some situations. Our objective of this paper is to propose a new and efficient active-set proximal quasi-Newton method for this problem. The idea behind is to speed up the convergence by separately handling the convergence of both the active and inactive variables. In particular, our method invokes a procedure to effectively estimate active and inactive variables, and then designs the search directions based on proximal gradients and quasi-Newton directions to efficiently treat the convergence of the active and inactive variables, respectively. We show that under some mild conditions, the global convergence is guaranteed, and the complexity is also performed to reveal the computational efficiency. Numerical experience on the -regularized quadratic programming and sparse principal component analysis on both synthetic and real data demonstrates its robustness and efficiency.

High-Contrast Reflection Tomography With Total-Variation Constraints

Inverse scattering is the process of estimating the spatial distribution of the scattering potential of an object by measuring the scattered wavefields around it. In this article, we consider reflection tomography of high contrast objects that commonly occurs in ground-penetrating radar, exploration geophysics, terahertz imaging, ultrasound, and electron microscopy. Unlike conventional transmission tomography, the reflection regime is severely ill-posed since the measured wavefields contain far less spatial frequency information of the target object. We propose a constrained incremental frequency inversion framework that requires no side information from a background model of the object. Our framework solves a sequence of regularized least-squares subproblems that ensure consistency with the measured scattered wavefield while imposing total-variation and non-negativity constraints. We propose a proximal Quasi-Newton method to solve the resulting subproblem and devise an automatic parameter selection routine to determine the constraint of each subproblem. We validate the performance of our approach on synthetic low-resolution phantoms and with a mismatched forward model test on a high-resolution phantom.

On Quasi-Newton Forward-Backward Splitting: Proximal Calculus and Convergence

We introduce a framework for quasi-Newton forward--backward splitting algorithms (proximal quasi-Newton methods) with a metric induced by diagonal $\pm$ rank-$r$ symmetric positive definite matrices. This special type of metric allows for a highly efficient evaluation of the proximal mapping. The key to this efficiency is a general proximal calculus in the new metric. By using duality, formulas are derived that relate the proximal mapping in a rank-$r$ modified metric to the original metric. We also describe efficient implementations of the proximity calculation for a large class of functions; the implementations exploit the piece-wise linear nature of the dual problem. Then, we apply these results to acceleration of composite convex minimization problems, which leads to elegant quasi-Newton methods for which we prove convergence. The algorithm is tested on several numerical examples and compared to a comprehensive list of alternatives in the literature. Our quasi-Newton splitting algorithm with the prescribed metric compares favorably against state-of-the-art. The algorithm has extensive applications including signal processing, sparse recovery, machine learning and classification to name a few.

Stochastic proximal quasi-Newton methods for non-convex composite optimization

ABSTRACTIn this paper, we propose a generic algorithmic framework for stochastic proximal quasi-Newton (SPQN) methods to solve non-convex composite optimization problems. Stochastic second-order information is explored to construct proximal subproblem. Under mild conditions we show the non-asympotic convergence of the proposed algorithm to stationary point of original problems and analyse its computational complexity. Besides, we extend the proximal form of Polyak-Łojasiewicz (PL) inequality to constrained settings and obtain the constrained proximal PL (CP-PL) inequality. Under CP-PL inequality linear convergence rate of the proposed algorithm is achieved. Moreover, we propose a modified self-scaling symmetric rank one incorporated in the framework for SPQN method, which is called stochastic symmetric rank one method. Finally, we report some numerical experiments to reveal the effectiveness of the proposed algorithm.

Proximal quasi-Newton methods for regularized convex optimization with linear and accelerated sublinear convergence rates

A general, inexact, efficient proximal quasi-Newton algorithm for composite optimization problems has been proposed by Scheinberg and Tang (Math Program 160:495–529, 2016) and a sublinear global convergence rate has been established. In this paper, we analyze the global convergence rate of this method, in the both exact and inexact settings, in the case when the objective function is strongly convex. We also investigate a practical variant of this method by establishing a simple stopping criterion for the subproblem optimization. Furthermore, we consider an accelerated variant, based on FISTA of Beck and Teboulle (SIAM 2:183–202, 2009), to the proximal quasi-Newton algorithm. Jiang et al. (SIAM 22:1042–1064, 2012) considered a similar accelerated method, where the convergence rate analysis relies on very strong impractical assumptions on Hessian estimates. We present a modified analysis while relaxing these assumptions and perform a numerical comparison of the accelerated proximal quasi-Newton algorithm and the regular one. Our analysis and computational results show that acceleration may not bring any benefit in the quasi-Newton setting.

IMRO: A Proximal Quasi-Newton Method for Solving $\ell_1$-Regularized Least Squares Problems

We present a proximal quasi-Newton method in which the approximation of the Hessian has the special format of "identity minus rank one" (IMRO) in each iteration. The proposed structure enables us to effectively recover the proximal point. The algorithm is applied to $l_1$-regularized least square problem arising in many applications including sparse recovery in compressive sensing, machine learning and statistics. Our numerical experiment suggests that the proposed technique competes favourably with other state-of-the-art solvers for this class of problems. We also provide a complexity analysis for variants of IMRO, showing that it matches known best bounds.

Practical inexact proximal quasi-Newton method with global complexity analysis

Recently several methods were proposed for sparse optimization which make careful use of second-order information (Hsieh et al. in Sparse inverse covariance matrix estimation using quadratic approximation. In: NIPS, 2011; Yuan et al. in An improved GLMNET for l1-regularized logistic regression and support vector machines. National Taiwan University, Taipei City, 2011; Olsen et al. in Newton-like methods for sparse inverse covariance estimation. In: NIPS, 2012; Byrd et al. in A family of second-order methods for convex l1-regularized optimization. Technical report, 2012) to improve local convergence rates. These methods construct a composite quadratic approximation using Hessian information, optimize this approximation using a first-order method, such as coordinate descent and employ a line search to ensure sufficient descent. Here we propose a general framework, which includes slightly modified versions of existing algorithms and also a new algorithm, which uses limited memory BFGS Hessian approximations, and provide a novel global convergence rate analysis, which covers methods that solve subproblems via coordinate descent.

Proximal quasi-Newton methods for nondifferentiable convex optimization

. The method is based on Rockafellar’s proximal point algorithm and a cutting-plane technique. At each step, we use an approximate proximal point pa(xk) of xk to define a vk∈∂ekf(pa(xk)) with ek≤α∥vk∥, where α is a constant. The method monitors the reduction in the value of ∥vk∥ to identify when a line search on f should be used. The quasi-Newton step is used to reduce the value of ∥vk∥. Without the differentiability of f, the method converges globally and the rate of convergence is Q-linear. Superlinear convergence is also discussed to extend the characterization result of Dennis and More. Numerical results show the good performance of the method.