Concave function

About: Concave function is a research topic. Over the lifetime, 1415 publications have been published within this topic receiving 33278 citations.

Stochastic Primal-Dual Algorithms with Faster Convergence than O(1/√T) for Problems without Bilinear Structure.

Abstract: Previous studies on stochastic primal-dual algorithms for solving min-max problems with faster convergence heavily rely on the bilinear structure of the problem, which restricts their applicability to a narrowed range of problems. The main contribution of this paper is the design and analysis of new stochastic primal-dual algorithms that use a mixture of stochastic gradient updates and a logarithmic number of deterministic dual updates for solving a family of convex-concave problems with no bilinear structure assumed. Faster convergence rates than $O(1/\sqrt{T})$ with $T$ being the number of stochastic gradient updates are established under some mild conditions of involved functions on the primal and the dual variable. For example, for a family of problems that enjoy a weak strong convexity in terms of the primal variable and has a strongly concave function of the dual variable, the convergence rate of the proposed algorithm is $O(1/T)$. We also investigate the effectiveness of the proposed algorithms for learning robust models and empirical AUC maximization.

A refined convergence analysis of pDCA$_e$ with applications to simultaneous sparse recovery and outlier detection

Abstract: We consider the problem of minimizing a difference-of-convex (DC) function, which can be written as the sum of a smooth convex function with Lipschitz gradient, a proper closed convex function and a continuous possibly nonsmooth concave function. We refine the convergence analysis in [38] for the proximal DC algorithm with extrapolation (pDCA$_e$) and show that the whole sequence generated by the algorithm is convergent when the objective is level-bounded, {\em without} imposing differentiability assumptions in the concave part. Our analysis is based on a new potential function and we assume such a function is a Kurdyka-{\L}ojasiewicz (KL) function. We also establish a relationship between our KL assumption and the one used in [38]. Finally, we demonstrate how the pDCA$_e$ can be applied to a class of simultaneous sparse recovery and outlier detection problems arising from robust compressed sensing in signal processing and least trimmed squares regression in statistics. Specifically, we show that the objectives of these problems can be written as level-bounded DC functions whose concave parts are {\em typically nonsmooth}. Moreover, for a large class of loss functions and regularizers, the KL exponent of the corresponding potential function are shown to be 1/2, which implies that the pDCA$_e$ is locally linearly convergent when applied to these problems. Our numerical experiments show that the pDCA$_e$ usually outperforms the proximal DC algorithm with nonmonotone linesearch [24, Appendix A] in both CPU time and solution quality for this particular application.

Concavity of monotone matrix functions of finite order

Abstract: Let f (0, ∞) → R be a monotone matrix function of order n for some arbitrary but fixed value of n. We show that f is a matrix concave function of order [n/2] and that for all n-by-n positive semidefinite matrices A and B, and all unitarily invariant norms . Because f is not assumed to be a monotone matrix function of all orders, Loewner's integral representation of functions that are monotone of all orders is not applicable, instead we use the functional characterization of f in proving these results.

Global optimization under Lipschitzian constraints

Abstract: We will present a new method for finding the global minimum of a Lipschitzian function under Lipschitzian constraints. The method consists in converting the given problem into one of globally minimizing a concave function subject to a convex and a reverse convex constraints. The resulting algorithm is of the same complexity as the outer approximation algorithm for a concave minimization problem.

Revisiting the Hermite-Hadamard fractional integral inequality via a Green function

Abstract: The Hermite-Hadamard inequality by means of the Riemann-Liouville fractional integral operators is already known in the literature. In this paper, it is our purpose to reconstruct this inequality via a relatively new method called the green function technique. In the process, some identities are established. Using these identities, we obtain loads of new results for functions whose second derivative is convex, monotone and concave in absolute value. We anticipate that the method outlined in this article will stimulate further investigation in this direction.