Facto-CNN: Memory-Efficient CNN Training with Low-rank Tensor Factorization and Lossy Tensor Compression - researchr publication

researchr

You are not signed in
Sign in
Sign up

Seungtae Lee, Jonghwan Ko, Seokin Hong. Facto-CNN: Memory-Efficient CNN Training with Low-rank Tensor Factorization and Lossy Tensor Compression. In Berrin Yanikoglu, Wray L. Buntine, editors, Asian Conference on Machine Learning, 11-14 November 2023, Istanbul, Turkey. Volume 222 of Proceedings of Machine Learning Research, pages 662-677, PMLR, 2023. [doi]

Abstract is missing.

runs on WebDSL