Accelerating Large-Scale Inference with Anisotropic Vector Quantization
Accelerating Large-Scale Inference with Anisotropic Vector Quantization
Ruiqi Guo,Philip Sun,4 作者,Sanjiv Kumar
2019 · DBLP: conf/icml/GuoSLGSCK20
International Conference on Machine Learning · 引用数 469
TLDR
A family of anisotropic quantization loss functions is developed that leads to a new variant of vector quantization that more greatly penalizes the parallel component of a datapoint's residual relative to its orthogonal component.