A dual block-coordinate trust-region solver with random Fourier features trains KRR, KLR, and SVM on millions of samples with 1 to 5 GB GPU memory and accuracy matching or beating Falkon, EigenPro3, and ThunderSVM.
Aravkin, Robert Baraldi, and Dominique Orban
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Joker: Joint Optimization Framework for Lightweight Kernel Machines
A dual block-coordinate trust-region solver with random Fourier features trains KRR, KLR, and SVM on millions of samples with 1 to 5 GB GPU memory and accuracy matching or beating Falkon, EigenPro3, and ThunderSVM.