论文标题
有效的多票彩票：提高准确性，训练和推理速度
Efficient Multi-Prize Lottery Tickets: Enhanced Accuracy, Training, and Inference Speed
论文作者
论文摘要
最近，Diffenderfer和Kailkhura提出了一种新的范式，仅通过修剪和量化随机加权的全精度神经网络，以学习紧凑而高度准确的二进制神经网络。但是，这些多pribe门票（MPT）的准确性对最佳的修剪比率高度敏感，这限制了其适用性。此外，原始实施没有获得任何培训或推理速度益处。在本报告中，我们讨论了克服这些局限性的几项改进。我们通过对CIFAR-10进行实验来展示提出的技术的好处。
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.
