Position-based Scaled Gradient for Model Quantization and Sparse Training.
Year: 2020
Type: preprint
Abstract: We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly. First, we theoretically show that applying PSG to the standard gradient descent (GD), which is called PSGD, is equivalent to the GD in the warped weight space, a space made by warping the original weight space via an appropriately designed invertible function. Second, we empirically show that PSG acting as a regularizer to a weight vector is very useful in model compression domains such as quantization and sparse training. PSG reduces the gap between the weight distributions of a full-precision model and its compressed counterpart. This enables the versatile deployment of a model either as an uncompressed mode or as a compressed mode depending on the availability of resources. The experimental results on CIFAR-10/100 and Imagenet datasets show the effectiveness of the proposed PSG in both domains of sparse training and quantization even for extremely low bits.
Source: arXiv (Cornell University)
Authors: Jangho Kim, KiYoon Yoo, Nojun Kwak
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3028224987