Fundamental limits of over-the-air optimization: Are analog schemes optimal?

arXiv2109.05222MaRDI QIDQ6377386

Author name not available (Why is that?)

Publication date: 11 September 2021

Abstract: We consider over-the-air convex optimization on a $d-$dimensional space where coded gradients are sent over an additive Gaussian noise channel with variance $sigm{a}^2$. The codewords satisfy an average power constraint $P$, resulting in the signal-to-noise ratio (SNR) of $P/sigm{a}^2$. We derive bounds for the convergence rates for over-the-air optimization. Our first result is a lower bound for the convergence rate showing that any code must slowdown the convergence rate by a factor of roughly $sqrtd/log(1+mathttSNR)$. Next, we consider a popular class of schemes called $analog$ $coding$, where a linear function of the gradient is sent. We show that a simple scaled transmission analog coding scheme results in a slowdown in convergence rate by a factor of $sqrtd(1+1/mathttSNR)$. This matches the previous lower bound up to constant factors for low SNR, making the scaled transmission scheme optimal at low SNR. However, we show that this slowdown is necessary for any analog coding scheme. In particular, a slowdown in convergence by a factor of $sqrtd$ for analog coding remains even when SNR tends to infinity. Remarkably, we present a simple quantize-and-modulate scheme that uses $Amplitude$ $Shift$ $Keying$ and almost attains the optimal convergence rate at all SNRs.

Has companion code repository: https://github.com/shubhamjha-46/ota_optimization

This page was built for publication: Fundamental limits of over-the-air optimization: Are analog schemes optimal?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6377386)