走向最佳跑步竞赛:应用于深度学习校准
Toward Optimal Run Racing: Application to Deep Learning Calibration
摘要:
本文旨在研究深度神经网络的一次性学习,其中考虑高度并行的设置来解决算法校准问题-选择最佳神经架构并根据手头的数据集学习超参数值。通过检测和提前停止非最佳运行,以最佳方式减少了众所周知的昂贵校准问题。理论上的贡献考虑多假设检验框架内的最优性保证。在Cifar 10、PTB和Wiki基准测试上的实验证明了该方法的相关性,它在没有额外超参数的情况下对最先进的技术进行了原则性和一致性的改进。
英文摘要:
This paper aims at one-shot learning of deep neural nets, where a highly parallel setting is considered to address the algorithm calibration problem - selecting the best neural architecture and learning hyper-parameter values depending on the dataset at hand. The notoriously expensive calibration problem is optimally reduced by detecting and early stopping non-optimal runs. The theoretical contribution regards the optimality guarantees within the multiple hypothesis testing framework. Experimentations on the Cifar10, PTB and Wiki benchmarks demonstrate the relevance of the approach with a principled and consistent improvement on the state of the art with no extra hyper-parameter.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。