Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning

We consider the problem of maximizing the $\ell_1$ norm of a linear map over the sphere, which arises in various machine learning applications such as orthogonal dictionary learning (ODL) and robust subspace recovery (RSR). The problem is numerically challenging due to its nonsmooth objective and nonconvex constraint, and its algorithmic aspects have not been well … Read more

Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold

We consider optimization problems over the Stiefel manifold whose objective function is the summation of a smooth function and a nonsmooth function. Existing methods for solving this kind of problems can be classified into three classes. Algorithms in the first class rely on information of the subgradients of the objective function and thus tend to … Read more

Vector Transport-Free SVRG with General Retraction for Riemannian Optimization: Complexity Analysis and Practical Implementation

In this paper, we propose a vector transport-free stochastic variance reduced gradient (SVRG) method with general retraction for empirical risk minimization over Riemannian manifold. Existing SVRG methods on manifold usually consider a specific retraction operation, and involve additional computational costs such as parallel transport or vector transport. The vector transport-free SVRG with general retraction we … Read more

Ambiguous Probabilistic Programs

Probabilistic programs are widely used decision models. When implemented in practice, however, there often exists distributional ambiguity in these models. In this paper, we model the ambiguity using the likelihood ratio (LR) and use LR to construct various ambiguity sets. We consider ambiguous probabilistic programs which optimize under the worst case. Ambiguous probabilistic programs can … Read more

Hardness and Approximation Results for hBcBall Constrained Homogeneous Polynomial Optimization Problems

In this paper, we establish hardness and approximation results for various $L_p$-ball constrained homogeneous polynomial optimization problems, where $p \in [2,\infty]$. Specifically, we prove that for any given $d \ge 3$ and $p \in [2,\infty]$, both the problem of optimizing a degree-$d$ homogeneous polynomial over the $L_p$-ball and the problem of optimizing a degree-$d$ multilinear … Read more

Chance-Constrained Linear Matrix Inequalities with Dependent Perturbations: A Safe Tractable Approximation Approach

The wide applicability of chance-constrained programming, together with advances in convex optimization and probability theory, has created a surge of interest in finding efficient methods for processing chance constraints in recent years. One of the successes is the development of so-called safe tractable approximations of chance-constrained programs, where a chance constraint is replaced by a … Read more

Improved Approximation Bound for Quadratic Optimization Problems with Orthogonality Constraints

In this paper we consider approximation algorithms for a class of quadratic optimization problems that contain orthogonality constraints, i.e. constraints of the form $X^TX=I$, where $X \in {\mathbb R}^{m \times n}$ is the optimization variable. Such class of problems, which we denote by (QP-OC), is quite general and captures several well–studied problems in the literature … Read more

A Unified Theorem on SDP Rank Reduction

We consider the problem of finding a low-rank approximate solution to a system of linear equations in symmetric, positive semidefinite matrices. Specifically, let $A_1,\ldots,A_m \in \R^{n\times n}$ be symmetric, positive semidefinite matrices, and let $b_1,\ldots,b_m \ge 0$. We show that if there exists a symmetric, positive semidefinite matrix $X$ to the system $A_i \bullet X … Read more

Theory of Semidefinite Programming for Sensor Network Localization

We analyze the semidefinite programming (SDP) based model and method for the position estimation problem in sensor network localization and other Euclidean distance geometry applications. We use SDP duality and interior–point algorithm theories to prove that the SDP localizes any network or graph that has unique sensor positions to fit given distance measures. Therefore, we … Read more