Over-the-air statistical estimation
Abstract/Contents
- Abstract
- The data fueling today's rise in machine learning is often generated by devices at the edge of a network, like sensors or mobile devices. To use all this data to train a common model, devices need to communicate something about their own data to a central server. But physical communication channels have limits, and these constraints are increasingly becoming the bottleneck in distributed and federated learning systems. Can we improve such learning algorithms by explicitly incorporating the physical communication layer into their design? We explore this question using a new framework that draws on wireless communication theory and statistical estimation. We propose "analog" estimation schemes that exploit the superposition inherent in multiple-access wireless networks, and analyze their performance. We then consider fundamental limits on how well "digital" schemes, which separate the communication and estimation stages, can possibly do. Comparing the two under several statistical models shows that the analog approach can yield drastic improvements in estimation error over the digital one. We also derive lower bounds for analog schemes that are within a logarithmic factor of our achievability results, and we present experimental results showing that these ideas can translate to performance gains in a federated machine learning context.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2021; ©2021 |
Publication date | 2021; 2021 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Lee, Chuan Zheng | |
---|---|---|
Degree supervisor | Özgür, Ayfer | |
Thesis advisor | Özgür, Ayfer | |
Thesis advisor | Van Roy, Benjamin | |
Thesis advisor | Weissman, Tsachy | |
Degree committee member | Van Roy, Benjamin | |
Degree committee member | Weissman, Tsachy | |
Associated with | Stanford University, Department of Electrical Engineering |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Chuan-Zheng Lee. |
---|---|
Note | Submitted to the Department of Electrical Engineering. |
Thesis | Thesis Ph.D. Stanford University 2021. |
Location | https://purl.stanford.edu/vj749dt7188 |
Access conditions
- Copyright
- © Copyright 2021 by Chuan Zheng Lee
Also listed in
Loading usage metrics...