VOCAL 2024
Abstract Submission

51. Nonlinear distributed estimation in correlated heavy-tailed noise

Invited abstract in session TB-4: Modeling, Simulation and Optimization, stream Large scale optimization and applications.

Thursday, 10:00 - 11:30
Room: C105

Authors (first author is the speaker)

1. Manojlo Vukovic
University of Novi Sad, Faculty of Technical Sciences, Faculty of Sciences
2. Dusan Jakovetic
University of Novi Sad Faculty of Sciences
3. Dragana Bajovic
Faculty of Technical Sciences, Univ. of Novi Sad
4. Soummya Kar
Carnegie Mellon University

Abstract

We consider distributed inference problems where N agents interconnected in a generic network collaborate to estimate an unknown constant vector parameter while continuously assimilating linear low-dimensional noisy observations of the parameter. Unlike most of existing studies, we focus on the scenario wherein both inter-agent communications and agent sensing are subject to mutually correlated, infinite-variance noises. We present nonlinear distributed estimators that provably work under this challenging setting. Analytical and numerical examples illustrate the findings.

Keywords

Status: accepted


Back to the list of papers