It Takes Two Moments: Rigidity and Limits of Continuous Encoders for Over-the-Air Computation
Abstract
We study over-the-air computation of functions, such as empirical variance, formed by combining two separately postprocessed sums of locally transformed observations. We consider continuous encoders subject to pointwise peak-power constraints over a single use of a complex multiple-access channel. With four or more transmitters, we identify conditions under which exact noiseless recovery forces every continuous encoder collection into a common affine structure that preserves both sums, reducing infinite-dimensional encoder design to selecting a finite set of coefficients. To quantify resilience against channel noise, we introduce a robustness score that measures the separation of noiseless received aggregates relative to variations in the desired function value. Within this characterized encoder family, we formulate robustness maximization as an exact convex semi-infinite program, eliminating rank constraints without a relaxation gap, and construct a decoder that attains the minimum uniform noise-amplification constant. For several function classes, including empirical variance, we derive closed-form robustness-optimal encoders and scores. Under mild regularity conditions, we also establish sharp limits on the Gaussian mean squared error at high signal-to-noise ratios and show how using the input distribution reduces average error at the expense of uniform robustness.
Related
- Subcritical limits of a 1D KPZ growth surface with finite moments
- Gaussian Limits for SGD Without Stationary Moments
- Certified computation of Buehler confidence limits for system reliability
- Einstein metrics at conical limits: stability, disconnected moduli, and entropy rigidity
- One-Cut Risk Profiles under Quadratic Loss: Discrete Convexity, Continuous Limits, and Higher Dimensions
BibTeX
@misc{razavikia2026takes,
title = {{It Takes Two Moments: Rigidity and Limits of Continuous Encoders for Over-the-Air Computation}},
author = {Saeed Razavikia},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.21536},
eprint = {2610.21536},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.21536},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - It Takes Two Moments: Rigidity and Limits of Continuous Encoders for Over-the-Air Computation
AU - Saeed Razavikia
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.21536
UR - https://arxiv.org/abs/2610.21536
AB - We study over-the-air computation of functions, such as empirical variance, formed by combining two separately postprocessed sums of locally transformed observations. We consider continuous encoders subject to pointwise peak-power constraints over a single use of a complex multiple-access channel. With four or more transmitters, we identify conditions under which exact noiseless recovery forces every continuous encoder collection into a common affine structure that preserves both sums, reducing infinite-dimensional encoder design to selecting a finite set of coefficients. To quantify resilience against channel noise, we introduce a robustness score that measures the separation of noiseless received aggregates relative to variations in the desired function value. Within this characterized encoder family, we formulate robustness maximization as an exact convex semi-infinite program, eliminating rank constraints without a relaxation gap, and construct a decoder that attains the minimum uniform noise-amplification constant. For several function classes, including empirical variance, we derive closed-form robustness-optimal encoders and scores. Under mild regularity conditions, we also establish sharp limits on the Gaussian mean squared error at high signal-to-noise ratios and show how using the input distribution reduces average error at the expense of uniform robustness.
ER -