Blind federated learning at the wireless edge with low-resolution ADC and DAC

Simple item page
buir.contributor.authorTeğin, Büşra
buir.contributor.orcidTeğin, Büşra|0000-0002-3342-5414
dc.citation.epage7798en_US
dc.citation.issueNumber12en_US
dc.citation.spage7786en_US
dc.citation.volumeNumber20en_US
dc.contributor.authorTeğin, Büşra
dc.date.accessioned2022-02-05T11:21:50Z
dc.date.available2022-02-05T11:21:50Z
dc.date.issued2021-06-15
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractWe study collaborative machine learning systems where a massive dataset is distributed across independent workers which compute their local gradient estimates based on their own datasets. Workers send their estimates through a multipath fading multiple access channel with orthogonal frequency division multiplexing to mitigate the frequency selectivity of the channel. We assume that there is no channel state information (CSI) at the workers, and the parameter server (PS) employs multiple antennas to align the received signals. To reduce the power consumption and the hardware costs, we employ complex-valued low-resolution digital-to-analog converters (DACs) and analog-to-digital converters (ADCs), at the transmitter and the receiver sides, respectively, and study the effects of practical low-cost DACs and ADCs on the learning performance. Our theoretical analysis shows that the impairments caused by low-resolution DACs and ADCs, including those of one-bit DACs and ADCs, do not prevent the convergence of the federated learning algorithms, and the multipath channel effects vanish when a sufficient number of antennas are used at the PS. We also validate our theoretical results via simulations, and demonstrate that using low-resolution, even one-bit, DACs and ADCs causes only a slight decrease in the learning accuracy.en_US
dc.description.provenanceSubmitted by Evrim Ergin (eergin@bilkent.edu.tr) on 2022-02-05T11:21:50Z No. of bitstreams: 1 Blind_federated_learning_at_the_wireless_edge_with_low-resolution_ADC_and_DAC.pdf: 1489967 bytes, checksum: e8d5797d79712c54333616effc4b23ab (MD5)en
dc.description.provenanceMade available in DSpace on 2022-02-05T11:21:50Z (GMT). No. of bitstreams: 1 Blind_federated_learning_at_the_wireless_edge_with_low-resolution_ADC_and_DAC.pdf: 1489967 bytes, checksum: e8d5797d79712c54333616effc4b23ab (MD5) Previous issue date: 2021-06-15en
dc.identifier.doi10.1109/TWC.2021.3087594en_US
dc.identifier.eissn1558-2248
dc.identifier.issn1536-1276
dc.identifier.urihttp://hdl.handle.net/11693/77091
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://doi.org/10.1109/TWC.2021.3087594en_US
dc.source.titleIEEE Transactions on Wireless Communicationsen_US
dc.subjectDistributed machine learningen_US
dc.subjectFederated learningen_US
dc.subjectStochastic gradient descenten_US
dc.subjectWireless channelsen_US
dc.subjectOFDMen_US
dc.subjectLow-resolution DAC and ADCen_US
dc.subjectOne-bit DAC and ADCen_US
dc.titleBlind federated learning at the wireless edge with low-resolution ADC and DACen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Blind_federated_learning_at_the_wireless_edge_with_low-resolution_ADC_and_DAC.pdf
Size:
1.42 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering