arXiv subjects

Kim-Chuan Toh

Publications and source records attributed to Kim-Chuan Toh.

At least 127 records · Page 7Linked to original sources

arXiv2018

Solving the OSCAR and SLOPE Models Using a Semismooth Newton-Based Augmented Lagrangian Method

The octagonal shrinkage and clustering algorithm for regression (OSCAR), equipped with the $\ell_1$-norm and a pair-wise $\ell_{\infty}$-norm regularizer, is a useful tool for feature selection and grouping in high-dimensional data analysis. The computational challenge posed by OSCAR, for high dimensional and/or large sample size data, has not yet been well resolved due to the non-smoothness and inseparability of the regularizer involved. In this paper, we successfully resolve this numerical challenge by proposing a sparse semismooth Newton-based augmented Lagrangian method to solve the more general SLOPE (the sorted L-one penalized estimation) model. By appropriately exploiting the inherent sparse and low-rank property of the generalized Jacobian of the semismooth Newton system in the augmented Lagrangian subproblem, we show how the computational complexity can be substantially reduced. Our algorithm presents a notable advantage in the high-dimensional statistical regression settings. Numerical experiments are conducted on real data sets, and the results demonstrate that our algorithm is far superior, in both speed and robustness, than the existing state-of-the-art algorithms based on first-order iterative schemes, including the widely used accelerated proximal gradient (APG) method and the alternating direction method of multipliers (ADMM).

math.OC↗

arXiv2018

Computing the Best Approximation Over the Intersection of a Polyhedral Set and the Doubly Nonnegative Cone

This paper introduces an efficient algorithm for computing the best approximation of a given matrix onto the intersection of linear equalities, inequalities and the doubly nonnegative cone (the cone of all positive semidefinite matrices whose elements are nonnegative). In contrast to directly applying the block coordinate descent type methods, we propose an inexact accelerated (two-)block coordinate descent algorithm to tackle the four-block unconstrained nonsmooth dual program. The proposed algorithm hinges on the efficient semismooth Newton method to solve the subproblems, which have no closed form solutions since the original four blocks are merged into two larger blocks. The $O(1/k^2)$ iteration complexity of the proposed algorithm is established. Extensive numerical results over various large scale semidefinite programming instances from relaxations of combinatorial problems demonstrate the effectiveness of the proposed algorithm.

math.OC↗

arXiv2018

An Efficient Semismooth Newton Based Algorithm for Convex Clustering

Clustering may be the most fundamental problem in unsupervised learning which is still active in machine learning research because its importance in many applications. Popular methods like K-means, may suffer from instability as they are prone to get stuck in its local minima. Recently, the sum-of-norms (SON) model (also known as clustering path), which is a convex relaxation of hierarchical clustering model, has been proposed in [7] and [5] Although numerical algorithms like ADMM and AMA are proposed to solve convex clustering model [2], it is known to be very challenging to solve large-scale problems. In this paper, we propose a semi-smooth Newton based augmented Lagrangian method for large-scale convex clustering problems. Extensive numerical experiments on both simulated and real data demonstrate that our algorithm is highly efficient and robust for solving large-scale problems. Moreover, the numerical results also show the superior performance and scalability of our algorithm compared to existing first-order methods.

math.OC↗

arXiv2017

An efficient Hessian based algorithm for solving large-scale sparse group Lasso problems

The sparse group Lasso is a widely used statistical model which encourages the sparsity both on a group and within the group level. In this paper, we develop an efficient augmented Lagrangian method for large-scale non-overlapping sparse group Lasso problems with each subproblem being solved by a superlinearly convergent inexact semismooth Newton method. Theoretically, we prove that, if the penalty parameter is chosen sufficiently large, the augmented Lagrangian method converges globally at an arbitrarily fast linear rate for the primal iterative sequence, the dual infeasibility, and the duality gap of the primal and dual objective functions. Computationally, we derive explicitly the generalized Jacobian of the proximal mapping associated with the sparse group Lasso regularizer and exploit fully the underlying second order sparsity through the semismooth Newton method. The efficiency and robustness of our proposed algorithm are demonstrated by numerical experiments on both the synthetic and real data sets.

math.OC↗

arXiv2017

Fast algorithms for large scale generalized distance weighted discrimination

High dimension low sample size statistical analysis is important in a wide range of applications. In such situations, the highly appealing discrimination method, support vector machine, can be improved to alleviate data piling at the margin. This leads naturally to the development of distance weighted discrimination (DWD), which can be modeled as a second-order cone programming problem and solved by interior-point methods when the scale (in sample size and feature dimension) of the data is moderate. Here, we design a scalable and robust algorithm for solving large scale generalized DWD problems. Numerical experiments on real data sets from the UCI repository demonstrate that our algorithm is highly efficient in solving large scale problems, and sometimes even more efficient than the highly optimized LIBLINEAR and LIBSVM for solving the corresponding SVM problems.

math.OC↗

arXiv2017

On efficiently solving the subproblems of a level-set method for fused lasso problems

In applying the level-set method developed in [Van den Berg and Friedlander, SIAM J. on Scientific Computing, 31 (2008), pp.~890--912 and SIAM J. on Optimization, 21 (2011), pp.~1201--1229] to solve the fused lasso problems, one needs to solve a sequence of regularized least squares subproblems. In order to make the level-set method practical, we develop a highly efficient inexact semismooth Newton based augmented Lagrangian method for solving these subproblems. The efficiency of our approach is based on several ingredients that constitute the main contributions of this paper. Firstly, an explicit formula for constructing the generalized Jacobian of the proximal mapping of the fused lasso regularizer is derived. Secondly, the special structure of the generalized Jacobian is carefully extracted and analyzed for the efficient implementation of the semismooth Newton method. Finally, numerical results, including the comparison between our approach and several state-of-the-art solvers, on real data sets are presented to demonstrate the high efficiency and robustness of our proposed algorithm in solving challenging large-scale fused lasso problems.

math.OC↗

arXiv2017

On the R-superlinear convergence of the KKT residues generated by the augmented Lagrangian method for convex composite conic programming

Due to the possible lack of primal-dual-type error bounds, the superlinear convergence for the Karush-Kuhn-Tucker (KKT) residues of the sequence generated by augmented Lagrangian method (ALM) for solving convex composite conic programming (CCCP) has long been an outstanding open question. In this paper, we aim to resolve this issue by first conducting convergence rate analysis for the ALM with Rockafellar's stopping criteria under only a mild quadratic growth condition on the dual of CCCP. More importantly, by further assuming that the Robinson constraint qualification holds, we establish the R-superlinear convergence of the KKT residues of the iterative sequence under easy-to-implement stopping criteria {for} the augmented Lagrangian subproblems. Equipped with this discovery, we gain insightful interpretations on the impressive numerical performance of several recently developed semismooth Newton-CG based ALM solvers for solving linear and convex quadratic semidefinite programming.

math.OC↗

arXiv2017

Sparse-BSOS: a bounded degree SOS hierarchy for large scale polynomial optimization with sparsity

We provide a sparse version of the bounded degree SOS hierarchy BSOS [7] for polynomial optimization problems. It permits to treat large scale problems which satisfy a structured sparsity pattern. When the sparsity pattern satisfies the running intersection property this Sparse-BSOS hierarchy of semidefinite programs (with semidefinite constraints of fixed size) converges to the global optimum of the original problem. Moreover, for the class of SOS-convex problems, finite convergence takes place at the first step of the hierarchy, just as in the dense version.

math.OC↗

arXiv2017

A block symmetric Gauss-Seidel decomposition theorem for convex composite quadratic programming and its applications

For a symmetric positive semidefinite linear system of equations $\mathcal{Q} {\bf x} = {\bf b}$, where ${\bf x} = (x_1,\ldots,x_s)$ is partitioned into $s$ blocks, with $s \geq 2$, we show that each cycle of the classical block symmetric Gauss-Seidel (block sGS) method exactly solves the associated quadratic programming (QP) problem but added with an extra proximal term of the form $\frac{1}{2} \| {\bf x}-{\bf x}^k \|_{\mathcal T}^2$, where ${\mathcal T}$ is a symmetric positive semidefinite matrix related to the sGS decomposition and ${\bf x}^k$ is the previous iterate. By leveraging on such a connection to optimization, we are able to extend the result (which we name as the block sGS decomposition theorem) for solving a convex composite QP (CCQP) with an additional possibly nonsmooth term in $x_1$, i.e., $\min\{ p(x_1) + \frac{1}{2}\langle {\bf x},\, \mathcal{Q} {\bf x} \rangle -\langle {\bf b},\, {\bf x}\rangle\}$, where $p(\cdot)$ is a proper closed convex function. Based on the block sGS decomposition theorem, we are able to extend the classical block sGS method to solve a CCQP. In addition, our extended block sGS method has the flexibility of allowing for inexact computation in each step of the block sGS cycle. At the same time, we can also accelerate the inexact block sGS method to achieve an iteration complexity of $O(1/k^2)$ after performing $k$ block sGS cycles. As a {fundamental} building block, the block sGS decomposition theorem has played a key role in various recently developed algorithms such as the inexact semiproximal {ALM/ADMM} for linearly constrained multi-block convex composite conic programming (CCCP), and the accelerated block coordinate descent method for multi-block CCCP.

math.NA↗

arXiv2017

A highly efficient semismooth Newton augmented Lagrangian method for solving Lasso problems

We develop a fast and robust algorithm for solving large scale convex composite optimization models with an emphasis on the $\ell_1$-regularized least squares regression (Lasso) problems. Despite the fact that there exist a large number of solvers in the literature for the Lasso problems, we found that no solver can efficiently handle difficult large scale regression problems with real data. By leveraging on available error bound results to realize the asymptotic superlinear convergence property of the augmented Lagrangian algorithm, and by exploiting the second order sparsity of the problem through the semismooth Newton method, we are able to propose an algorithm, called {\sc Ssnal}, to efficiently solve the aforementioned difficult problems. Under very mild conditions, which hold automatically for Lasso problems, both the primal and the dual iteration sequences generated by {\sc Ssnal} possess a fast linear convergence rate, which can even be superlinear asymptotically. Numerical comparisons between our approach and a number of state-of-the-art solvers, on real data sets, are presented to demonstrate the high efficiency and robustness of our proposed algorithm in solving difficult large scale Lasso problems.

math.OC↗

arXiv2016

QSDPNAL: A two-phase augmented Lagrangian method for convex quadratic semidefinite programming

In this paper, we present a two-phase augmented Lagrangian method, called QSDPNAL, for solving convex quadratic semidefinite programming (QSDP) problems with constraints consisting of a large number of linear equality, inequality constraints, a simple convex polyhedral set constraint, and a positive semidefinite cone constraint. A first order algorithm which relies on the inexact Schur complement based decomposition technique is developed in QSDPNAL-Phase I with the aim of solving a QSDP problem to moderate accuracy or using it to generate a reasonably good initial point for the second phase. In QSDPNAL-Phase II, we design an augmented Lagrangian method (ALM) where the inner subproblem in each iteration is solved via inexact semismooth Newton based algorithms. Simple and implementable stopping criteria are designed for the ALM. Moreover, under mild conditions, we are able to establish the rate of convergence of the proposed algorithm and prove the R-(super)linear convergence of the KKT residual. In the implementation of QSDPNAL, we also develop efficient techniques for solving large scale linear systems of equations under certain subspace constraints. More specifically, simpler and yet better conditioned linear systems are carefully designed to replace the original linear systems and novel shadow sequences are constructed to alleviate the numerical difficulties brought about by the crucial subspace constraints. Extensive numerical results for various large scale QSDPs show that our two-phase algorithm is highly efficient and robust in obtaining accurate solutions.

math.OC↗

arXiv2016

On the Asymptotic Superlinear Convergence of the Augmented Lagrangian Method for Semidefinite Programming with Multiple Solutions

Solving large scale convex semidefinite programming (SDP) problems has long been a challenging task numerically. Fortunately, several powerful solvers including SDPNAL, SDPNAL+ and QSDPNAL have recently been developed to solve linear and convex quadratic SDP problems to high accuracy successfully. These solvers are based on the augmented Lagrangian method (ALM) applied to the dual problems with the subproblems being solved by semismooth Newton-CG methods. Noticeably, thanks to Rockafellar's general theory on the proximal point algorithms, the primal iteration sequence generated by the ALM enjoys an asymptotic Q-superlinear convergence rate under a second order sufficient condition {for the primal problem}. This second order sufficient condition implies that the primal problem has a unique solution, which can be restrictive in many applications. For gaining more insightful interpretations on the high efficiency of these solvers, in this paper we conduct an asymptotic superlinear convergence analysis of the ALM for convex SDP when the primal problem has multiple solutions (can be unbounded). Under a fairly mild second order growth condition, we prove that the primal iteration sequence generated by the ALM converges asymptotically Q-superlinearly, while the dual feasibility and the dual objective function value converge asymptotically R-superlinearly. Moreover, by studying the metric subregularity of the Karush-Kuhn-Tucker solution mapping, we also provide sufficient conditions to guarantee the asymptotic R-superlinear convergence of the dual iterate.

math.OC↗

arXiv2016

Max-Norm Optimization for Robust Matrix Recovery

This paper studies the matrix completion problem under arbitrary sampling schemes. We propose a new estimator incorporating both max-norm and nuclear-norm regularization, based on which we can conduct efficient low-rank matrix recovery using a random subset of entries observed with additive noise under general non-uniform and unknown sampling distributions. This method significantly relaxes the uniform sampling assumption imposed for the widely used nuclear-norm penalized approach, and makes low-rank matrix recovery feasible in more practical settings. Theoretically, we prove that the proposed estimator achieves fast rates of convergence under different settings. Computationally, we propose an alternating direction method of multipliers algorithm to efficiently compute the estimator, which bridges a gap between theory and practice of machine learning methods with max-norm regularization. Further, we provide thorough numerical studies to evaluate the proposed method using both simulated and real datasets.

stat.ML↗

arXiv2016

An Efficient Inexact Symmetric Gauss-Seidel Based Majorized ADMM for High-Dimensional Convex Composite Conic Programming

In this paper, we propose an inexact multi-block ADMM-type first-order method for solving a class of high-dimensional convex composite conic optimization problems to moderate accuracy. The design of this method combines an inexact 2-block majorized semi-proximal ADMM and the recent advances in the inexact symmetric Gauss-Seidel (sGS) technique for solving a multi-block convex composite quadratic programming whose objective contains a nonsmooth term involving only the first block-variable. One distinctive feature of our proposed method (the sGS-imsPADMM) is that it only needs one cycle of an inexact sGS method, instead of an unknown number of cycles, to solve each of the subproblems involved.With some simple and implementable error tolerance criteria, the cost for solving the subproblems can be greatly reduced, and many steps in the forward sweep of each sGS cycle can often be skipped, which further contributes to the efficiency of the proposed method. Global convergence as well as the iteration complexity in the non-ergodic sense is established.Preliminary numerical experiments on some high-dimensional linear and convex quadratic SDP problems with a large number of linear equality and inequality constraints are also provided. The results show that for the vast majority of the tested problems, the sGS-imsPADMM is 2 to 3 times faster than the directly extended multi-block ADMM with the aggressive step-length of 1.618, which is currently the benchmark among first-order methods for solving multi-block linear and quadratic SDP problems though its convergence is not guaranteed.

math.OC↗

arXiv2016

A Note on the Convergence of ADMM for Linearly Constrained Convex Optimization Problems

This note serves two purposes. Firstly, we construct a counterexample to show that the statement on the convergence of the alternating direction method of multipliers (ADMM) for solving linearly constrained convex optimization problems in a highly influential paper by Boyd et al. [Found. Trends Mach. Learn. 3(1) 1-122 (2011)] can be false if no prior condition on the existence of solutions to all the subproblems involved is assumed to hold. Secondly, we present fairly mild conditions to guarantee the existence of solutions to all the subproblems and provide a rigorous convergence analysis on the ADMM, under a more general and useful semi-proximal ADMM (sPADMM) setting considered by Fazel et al. [SIAM J. Matrix Anal. Appl. 34(3) 946-977 (2013)], with a computationally more attractive large step-length that can even exceed the practically much preferred golden ratio of $(1+\sqrt{5})/2$.

math.OC↗

arXiv2015

A Majorized ADMM with Indefinite Proximal Terms for Linearly Constrained Convex Composite Optimization

This paper presents a majorized alternating direction method of multipliers (ADMM) with indefinite proximal terms for solving linearly constrained $2$-block convex composite optimization problems with each block in the objective being the sum of a non-smooth convex function and a smooth convex function, i.e., $\min_{x \in {\cal X}, \; y \in {\cal Y}}\{p(x)+f(x) + q(y)+g(y)\mid A^* x+B^* y = c\}$. By choosing the indefinite proximal terms properly, we establish the global convergence and $O(1/k)$ ergodic iteration-complexity of the proposed method for the step-length $τ\in (0, (1+\sqrt{5})/2)$. The computational benefit of using indefinite proximal terms within the ADMM framework instead of the current requirement of positive semidefinite ones is also demonstrated numerically. This opens up a new way to improve the practical performance of the ADMM and related methods.

math.OC↗

arXiv2015

An Efficient Inexact ABCD Method for Least Squares Semidefinite Programming

We consider least squares semidefinite programming (LSSDP) where the primal matrix variable must satisfy given linear equality and inequality constraints, and must also lie in the intersection of the cone of symmetric positive semidefinite matrices and a simple polyhedral set. We propose an inexact accelerated block coordinate descent (ABCD) method for solving LSSDP via its dual, which can be reformulated as a convex composite minimization problem whose objective is the sum of a coupled quadratic function involving four blocks of variables and two separable non-smooth functions involving only the first and second block, respectively. Our inexact ABCD method has the attractive $O(1/k^2)$ iteration complexity if the subproblems are solved progressively more accurately. The design of our ABCD method relies on recent advances in the symmetric Gauss-Seidel technique for solving a convex minimization problem whose objective is the sum of a multi-block quadratic function and a non-smooth function involving only the first block. Extensive numerical experiments on various classes of over 600 large scale LSSDP problems demonstrate that our proposed ABCD method not only can solve the problems to high accuracy, but it is also far more efficient than (a) the well known BCD (block coordinate descent) method, (b) the eARBCG (an enhanced version of the accelerated randomized block coordinate gradient) method, and (c) the APG (accelerated proximal gradient) method.

math.OC↗

arXiv2015

On the convergence properties of a majorized ADMM for linearly constrained convex optimization problems with coupled objective functions

In this paper, we establish the convergence properties for a majorized alternating direction method of multipliers (ADMM) for linearly constrained convex optimization problems whose objectives contain coupled functions. Our convergence analysis relies on the generalized Mean-Value Theorem which plays an important role to properly control the cross terms due to the presence of coupled objective functions. Our results in particular show that directly applying 2-block ADMM with a large step length to the linearly constrained convex optimization problem with a quadratically coupled objective function is convergent under mild conditions. We also provide several iteration complexity results for the algorithm.

math.OC↗