Jha, SK and Mayekar, P and Tyagi, H (2021) Fundamental limits of over-the-air optimization: Are analog schemes optimal? In: 2021 IEEE Global Communications Conference, GLOBECOM 2021, 7 - 11 December 2021, Madrid.
|
PDF
IEEE_GLOBECOM_2021.pdf - Published Version Download (412kB) | Preview |
Abstract
We consider convex optimization on a d dimensional space where coded gradients are sent over an additive Gaussian noise channel with variance sigma2. The codewords satisfy an average power constraint P, resulting in the signal-to-noise ratio (SNR) of P/sigma2. Many schemes have been proposed for this problem, termed over-the-air optimization, in recent years. We present lower and upper 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 d/log(1+textSNR). 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 d(1+1SNR). 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 d remains even when SNR tends to infinity, a clear shortcoming of analog coding schemes at high SNR. Remarkably, we present a simple quantize-and-modulate scheme that uses Amplitude Shift Keying and almost attains the optimal convergence rate at all SNRs. © 2021 IEEE.
| Item Type: | Conference Proceedings |
|---|---|
| Publication: | 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings |
| Publisher: | Institute of Electrical and Electronics Engineers Inc. |
| Additional Information: | The copyright for this article belongs to authors. |
| Keywords: | Convex optimization; Gaussian noise (electronic); Transmissions, Analog coding; Coding scheme; Convergence rates; Convex optimisation; Low bound; Low signal-to-noise ratio; Optimisations; Over the airs; Schemes optimal; Simple++, Signal to noise ratio |
| Department/Centre: | Division of Electrical Sciences > Electrical Communication Engineering |
| Date Deposited: | 19 May 2022 10:43 |
| Last Modified: | 19 May 2022 10:43 |
| URI: | https://eprints.iisc.ac.in/id/eprint/71904 |
Actions (login required)
 |
View Item |
