arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.04522cs.LGstat.ML
收藏

跨超参数设置的学习曲线外推的概率卷展栏

Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

University of Freiburg(弗赖堡大学);Bosch Center for Artificial Intelligence(博世人工智能中心)

Matilde Gargiani, Aaron Klein, Stefan Falkner, Frank Hutter

摘要:

我们提出了概率模型,可以基于具有可变长度学习曲线的训练数据外推迭代机器学习算法的学习曲线,例如用于训练深度网络的随机梯度下降。我们研究这个框架的基础上随机森林和贝叶斯循环神经网络的实例。我们的实验表明,当外推使用不同超参数设置训练的神经网络的性能时,这些模型比来自超参数优化文献的最新模型产生更好的预测。

英文摘要:

We propose probabilistic models that can extrapolate learning curves of iterative machine learning algorithms, such as stochastic gradient descent for training deep networks, based on training data with variable-length learning curves. We study instantiations of this framework based on random forests and Bayesian recurrent neural networks. Our experiments show that these models yield better predictions than state-of-the-art models from the hyperparameter optimization literature when extrapolating the performance of neural networks trained with different hyperparameter settings.

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。

↑