Over-the-Air Statistical Estimation
Not on the map. Why?
Abstract (arXiv)
We study schemes and lower bounds for distributed minimax statistical estimation over a Gaussian multiple-access channel (MAC) under squared error loss, in a framework combining statistical estimation and wireless communication. First, we develop "analog" joint estimation-communication schemes that exploit the superposition property of the Gaussian MAC and we characterize their risk in terms of the number of nodes and dimension of the parameter space. Then, we derive information-theoretic lower bounds on the minimax risk of any estimation scheme restricted to communicate the samples over a given number of uses of the channel and show that the risk achieved by our proposed schemes is within a logarithmic factor of these lower bounds. We compare both achievability and lower bound results to previous "digital" lower bounds, where nodes transmit errorless bits at the Shannon capacity of the MAC, showing that estimation schemes that leverage the physical layer offer a drastic reduction in estimation error over digital schemes relying on a physical-layer abstraction.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 6 Mar 2021.
Builds on
25 of 44 references.
References · 25
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
- 2018Federated Learning via Over-the-Air Computationcited by 215
- 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
- 2019Federated Learning over Wireless Fading Channelscited by 178
- 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
- 2019Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanismcited by 75
- 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
- 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 62
- 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
- 2015Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequalitycited by 50
- 2020Wireless Federated Learning with Local Differential Privacycited by 50
- 2019Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Datacited by 39
13 more
- 2018Geometric Lower Bounds for Distributed Parameter Estimation under Communication Constraintscited by 33
- 2018Inference under Information Constraints I: Lower Bounds from Chi-Square Contractioncited by 31
- 2020Convergence of Federated Learning over a Noisy Downlinkcited by 29
- 2020rTop-k: A Statistical Estimation Approach to Distributed SGDcited by 27
- 2019Over-the-Air Computation Systems: Optimization, Analysis and Scaling Lawscited by 25
- 2014On Communication Cost of Distributed Statistical Estimation and Dimensionalitycited by 24
- 2020Fisher information under local differential privacycited by 22
- 2018Blind Over-the-Air Computation and Data Fusion via Provable Wirtinger Flowcited by 8
- 2020Over-the-Air Computation Systems: Optimal Design with Sum-Power Constraintcited by 8
- 2020Gradient Statistics Aware Power Control for Over-the-Air Federated Learningcited by 5
- 2019Lower Bounds for Learning Distributions under Communication Constraints via Fisher Informationcited by 4
- 2015STAC: Simultaneous Transmitting and Air Computing in Wireless Data Center Networkscited by 2
- 2020Blind Federated Learning at the Wireless Edge with Low-Resolution ADC and DACcited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 2.
3 papers.