# Instant Quantization of Neural Networks using Monte Carlo Methods

arXiv: https://arxiv.org/abs/1905.12253 · HTML: https://mlsanity.com/paper/1905.12253/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 4 of 4)

- [Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices](https://mlsanity.com/paper/2103.17142/) (2021)
- [Artificial Neural Networks generated by Low Discrepancy Sequences](https://mlsanity.com/paper/2103.03543/) (2021)
- [Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing](https://mlsanity.com/paper/2103.11912/) (2021)
- [SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness](https://mlsanity.com/paper/2211.11561/) (2022)

## Abstract (arXiv)

Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption. We propose Monte Carlo methods to quantize the weights and activations of pre-trained neural networks without any re-training. By performing importance sampling we obtain quantized low bit-width integer values from full-precision weights and activations. The precision, sparsity, and complexity are easily configurable by the amount of sampling performed. Our approach, called Monte Carlo Quantization (MCQ), is linear in both time and space, with the resulting quantized, sparse networks showing minimal accuracy loss when compared to the original full-precision networks. Our method either outperforms or achieves competitive results on multiple benchmarks compared to previous quantization methods that do require additional training.