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.
@article{arxiv.2209.12839,
title = {Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed},
author = {Hao Cheng and Pu Zhao and Yize Li and Xue Lin and James Diffenderfer and Ryan Goldhahn and Bhavya Kailkhura},
journal= {arXiv preprint arXiv:2209.12839},
year = {2022}
}