# On Periodic Functions as Regularizers for Quantization of Neural Networks

arXiv: https://arxiv.org/abs/1811.09862 · HTML: https://mlsanity.com/paper/1811.09862/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification](https://mlsanity.com/paper/2205.07877/) (2022)
- [Channel-Wise Mixed-Precision Quantization for Large Language Models](https://mlsanity.com/paper/2410.13056/) (2024)
- [Coresets for Data Discretization and Sine Wave Fitting](https://mlsanity.com/paper/2203.03009/) (2022)
- [End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs](https://mlsanity.com/paper/2304.06745/) (2023)
- [Enhancing Cross-Category Learning in Recommendation Systems with Multi-Layer Embedding Training](https://mlsanity.com/paper/2309.15881/) (2023)
- [Unsupervised Complex Semi-Binary Matrix Factorization for Activation Sequence Recovery of Quasi-Stationary Sources](https://mlsanity.com/paper/2310.02295/) (2023)
- [Cauchy-Schwarz Regularizers](https://mlsanity.com/paper/2503.01639/) (2025)

## Abstract (arXiv)

Deep learning models have been successfully used in computer vision and many other fields. We propose an unorthodox algorithm for performing quantization of the model parameters. In contrast with popular quantization schemes based on thresholds, we use a novel technique based on periodic functions, such as continuous trigonometric sine or cosine as well as non-continuous hat functions. We apply these functions component-wise and add the sum over the model parameters as a regularizer to the model loss during training. The frequency and amplitude hyper-parameters of these functions can be adjusted during training. The regularization pushes the weights into discrete points that can be encoded as integers. We show that using this technique the resulting quantized models exhibit the same accuracy as the original ones on CIFAR-10 and ImageNet datasets.