arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1905.13360cs.LGstat.ML
收藏

高效的前向架构搜索

Efficient Forward Architecture Search

Carnegie Mellon University(卡内基梅隆大学);Microsoft Research(微软研究院)

Hanzhang Hu, John Langford, Rich Caruana, Saurajit Mukherjee, Eric Horvitz, Debadeepta Dey

摘要:

我们提出了一个神经架构搜索(NAS)算法,Petridish,迭代地添加快捷连接到现有的网络层。添加的快捷连接有效地在增强层上执行梯度提升。该算法的动机是由特征选择算法向前逐步线性回归,因为我们认为NAS作为一个泛化的特征选择回归,其中NAS选择层之间的捷径,而不是选择功能。为了减少可能的连接组合的试验次数,我们在每个生长阶段联合训练所有可能的连接,同时利用特征选择技术来选择它们的子集。我们的实验表明,这个过程是一个有效的前向架构搜索算法,可以找到竞争力的模型,使用几个GPU天在搜索空间的可重复的网络模块(细胞搜索)和空间的一般网络(宏搜索)。Petridish特别适合于从对终身学习场景至关重要的现有模型中进行热启动。

英文摘要:

We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers. The added shortcut connections effectively perform gradient boosting on the augmented layers. The proposed algorithm is motivated by the feature selection algorithm forward stage-wise linear regression, since we consider NAS as a generalization of feature selection for regression, where NAS selects shortcuts among layers instead of selecting features. In order to reduce the number of trials of possible connection combinations, we train jointly all possible connections at each stage of growth while leveraging feature selection techniques to choose a subset of them. We experimentally show this process to be an efficient forward architecture search algorithm that can find competitive models using few GPU days in both the search space of repeatable network modules (cell-search) and the space of general networks (macro-search). Petridish is particularly well-suited for warm-starting from existing models crucial for lifelong-learning scenarios.

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。

↑