# Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed

arXiv: https://arxiv.org/abs/2209.12839 · HTML: https://mlsanity.com/paper/2209.12839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 6 of 6)

- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Rethinking the Hyperparameters for Fine-tuning](https://mlsanity.com/paper/2002.11770/) (2020)
- [Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network](https://mlsanity.com/paper/2103.09377/) (2021)
- [PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices](https://mlsanity.com/paper/1909.05073/) (2019)
- [Powerpropagation: A sparsity inducing weight reparameterisation](https://mlsanity.com/paper/2110.00296/) (2021)
- [Unsupervised Finetuning](https://mlsanity.com/paper/2110.09510/) (2021)

## Abstract (arXiv)

Recently, Diffenderfer and Kailkhura proposed a new paradigm for learning compact yet highly accurate binary neural networks simply by pruning and quantizing randomly weighted full precision neural networks. However, the accuracy of these multi-prize tickets (MPTs) is highly sensitive to the optimal prune ratio, which limits their applicability. Furthermore, the original implementation did not attain any training or inference speed benefits. In this report, we discuss several improvements to overcome these limitations. We show the benefit of the proposed techniques by performing experiments on CIFAR-10.