Year: 2017
Type: conference-paper
Abstract: We consider a non-convex constrained Lagrangian formulation of a fundamental bi-criteria optimization problem for variable selection in statistical learning; the two criteria are a smooth (possibly) non-convex loss function, measuring the fitness of the model to data, and the latter function is a difference-of-convex (DC) regularization, employed to promote some extra structure on the solution, like sparsity. This general class of nonconvex problems arises in many big-data applications, from statistical machine learning to physical sciences and engineering. We develop the first unified distributed algorithmic framework for these problems and establish its asymptotic convergence to d-stationary solutions. Two key features of the method are: i) it can be implemented on arbitrary networks (digraphs) with (possibly) time-varying connectivity; and ii) it does not require the restrictive assumption that the (sub)gradient of the objective function is bounded, which enlarges significantly the class of statistical learning problems that can be solved with convergence guarantees.
Authors: Ying Sun, Gesualdo Scutari
Institution: Purdue University West Lafayette
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Awards: CAREER:Variational Inequalities: A New Paradigm for Cognitive Network Layering, CIF: Small: Collaborative Research: Communicating While Computing: Mobile Fog Computing Over Wireless Heterogeneous Networks, G4784054808, G6671297155, CIF: Small: Collaborative Research: Parallel Online Algorithms for Large-Scale MRI, G8876996369
OpenAlex ID: W2553773573
