Soft Quantization: Model Compression Via Weight Coupling

📅 2026-01-29
📈 Citations: 0
Influential: 0
📄 PDF

career value

204K/year
🤖 AI Summary
This work addresses the challenge of balancing accuracy and generalization in neural network quantization by proposing a soft quantization method during training. The approach introduces short-range attractive coupling among weights to encourage automatic discretization of the weight distribution, enabling mixed-precision compression without complex scheduling schemes. Relying on only two hyperparameters, the method offers both simplicity and flexibility, providing a novel tool for studying the trade-off between model compression and generalization. Experimental results on ResNet-20 with CIFAR-10 demonstrate that the proposed technique outperforms post-training quantization methods based on histogram equalization, achieving higher accuracy in compressed models.

Technology Category

Application Category

📝 Abstract
We show that introducing short-range attractive couplings between the weights of a neural network during training provides a novel avenue for model quantization. These couplings rapidly induce the discretization of a model's weight distribution, and they do so in a mixed-precision manner despite only relying on two additional hyperparameters. We demonstrate that, within an appropriate range of hyperparameters, our"soft quantization''scheme outperforms histogram-equalized post-training quantization on ResNet-20/CIFAR-10. Soft quantization provides both a new pipeline for the flexible compression of machine learning models and a new tool for investigating the trade-off between compression and generalization in high-dimensional loss landscapes.
Problem

Research questions and friction points this paper is trying to address.

model compression
quantization
weight coupling
generalization
neural networks
Innovation

Methods, ideas, or system contributions that make the work stand out.

soft quantization
weight coupling
model compression
mixed-precision quantization
neural network training
D
Daniel T. Bernstein
Center for the Physics of Biological Function, Princeton, NJ, USA; Lewis-Sigler Institute, Princeton, NJ, USA
L
Luca di Carlo
Center for the Physics of Biological Function, Princeton, NJ, USA; Joseph Henry Laboratories of Physics, Princeton, NJ, USA
D
David J. Schwab
Initiative for the Theoretical Sciences, CUNY Graduate Center, New York City, NY, USA