Technical Program

Paper Detail

Paper Title Improved bounds on Gaussian MAC and sparse regression via Gaussian inequalities
Paper IdentifierMO3.R6.2
Authors Ilias Zadik, Yury Polyanskiy, Massachusetts Institute of Technology, United States; Christos Thrampoulidis, University of California, Santa Barbara, United States
Session Multiple Access Channels
Location Sorbonne, Level 5
Session Time Monday, 08 July, 14:30 - 16:10
Presentation Time Monday, 08 July, 14:50 - 15:10
Manuscript  Click here to download the manuscript
Abstract We consider the Gaussian multiple-access channel with two critical departures from the classical asymptotics: a) number of users proportional to blocklength and b) each user sends a fixed number of data bits. We provide improved bounds on the tradeoff between the user density and the energy-per-bit. Interestingly, in this information-theoretic problem we rely on Gordon's lemma from Gaussian process theory. From the engineering standpoint, we discover a surprising new effect: good coded-access schemes can achieve perfect multi-user interference cancellation at low user density. In addition, by a similar method we analyze the limits of false-discovery in binary sparse regression problem in the asymptotic regime of number of measurements going to infinity at fixed ratios with problem dimension, sparsity and noise level. Our rigorous bound matches the formal replica-method prediction for some range of parameters with imperceptible numerical precision.