# RPR: Random Partition Relaxation for Training; Binary and Ternary Weight Neural Networks

arXiv: https://arxiv.org/abs/2001.01091 · HTML: https://mlsanity.com/paper/2001.01091/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2020.

## Built on by (most cited first, 2 of 2)

- [Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference](https://mlsanity.com/paper/2202.07462/) (2022)
- [Ternary Quantization: A Survey](https://mlsanity.com/paper/2303.01505/) (2023)

## Abstract (arXiv)

We present Random Partition Relaxation (RPR), a method for strong quantization of neural networks weight to binary (+1/-1) and ternary (+1/0/-1) values. Starting from a pre-trained model, we quantize the weights and then relax random partitions of them to their continuous values for retraining before re-quantizing them and switching to another weight partition for further adaptation. We demonstrate binary and ternary-weight networks with accuracies beyond the state-of-the-art for GoogLeNet and competitive performance for ResNet-18 and ResNet-50 using an SGD-based training method that can easily be integrated into existing frameworks.