Výsledky vyhledávání - "Model compression algorithms"
-
1
Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes
ISSN: 2641-9874Vydáno: IEEE 20.05.2024Vydáno v Annual Joint Conference of the IEEE Computer and Communications Societies (20.05.2024)“… Model compression algorithms, such as quantization and sparsification, have been suggested but they generally assume a fixed code length, which does not reflect the heterogeneity and variability of model updates…”
Získat plný text
Konferenční příspěvek -
2
Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes
ISSN: 2331-8422Vydáno: Ithaca Cornell University Library, arXiv.org 06.02.2024Vydáno v arXiv.org (06.02.2024)“… Model compression algorithms, such as quantization and sparsification, have been suggested but they generally assume a fixed code length, which does not reflect the heterogeneity and variability of model updates…”
Získat plný text
Paper