Abstract: Quantization is a common method to improve communication efficiency in federated learning (FL) by compressing the gradients that clients upload. Currently, most application scenarios involve ...
This repository contains the official implementation of Robust Residual Finite Scalar Quantization (RFSQ), a novel quantization framework that addresses the residual magnitude decay problem in naive ...
The fastest and most accurate quantization method for high-dimensional vectors. Our project introduces Segmented Code Adjustment Quantization (SAQ), a novel quantization algorithm built upon dimension ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results