Efficient Federated Low Rank Matrix Recovery via Alternating GD and Minimization: A Simple Proof

This note provides a significantly simpler and shorter proof of our sample complexity guarantee for solving the low rank column-wise sensing problem using the Alternating Gradient Descent (GD) and Minimization (AltGDmin) algorithm. AltGDmin was developed and analyzed for solving this problem in our...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on information theory Ročník 70; číslo 7; s. 5162 - 5167
Hlavný autor: Vaswani, Namrata
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.07.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Complexity theory
federated learning
Low rank column-wise sensing (LRCS)
Minimization
multi-task representation learning
Optimization
Partitioning algorithms
Sensors
Time complexity
Vectors
ISSN:0018-9448, 1557-9654
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This note provides a significantly simpler and shorter proof of our sample complexity guarantee for solving the low rank column-wise sensing problem using the Alternating Gradient Descent (GD) and Minimization (AltGDmin) algorithm. AltGDmin was developed and analyzed for solving this problem in our recent work. We also provide an improved guarantee.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9448
1557-9654
DOI:10.1109/TIT.2024.3365795