arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.02777cs.LGstat.ML
收藏

门控神经网络的学习

Learning in Gated Neural Networks

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Washington(华盛顿大学)

Ashok Vardhan Makkuva, Sewoong Oh, Sreeram Kannan, Pramod Viswanath

摘要:

门控是现代神经网络(包括LSTM、GRU和稀疏门控深度神经网络)中的关键特征。这种门控网络的主干是一个专家混合层,其中几个专家做出回归决策,门控控制如何以依赖于输入的方式权衡决策。尽管在现代和经典的机器学习中具有如此突出的作用,但是对专家混合的参数恢复知之甚少,因为已知梯度下降和EM算法在此类模型中陷入局部最优。在本文中,我们对优化前景进行了仔细的分析,并表明通过适当设计的损失函数,梯度下降确实可以准确地学习参数。支撑我们的结果的一个关键思想是两个{ \em不同}损失函数的设计,一个用于恢复专家参数和另一个用于恢复门控参数。我们证明了第一个样本的复杂性结果参数恢复在这个模型中的任何算法,并证明了显着的性能增益超过标准的损失函数的数值实验。

英文摘要:

Gating is a key feature in modern neural networks including LSTMs, GRUs and sparsely-gated deep neural networks. The backbone of such gated networks is a mixture-of-experts layer, where several experts make regression decisions and gating controls how to weigh the decisions in an input-dependent manner. Despite having such a prominent role in both modern and classical machine learning, very little is understood about parameter recovery of mixture-of-experts since gradient descent and EM algorithms are known to be stuck in local optima in such models. In this paper, we perform a careful analysis of the optimization landscape and show that with appropriately designed loss functions, gradient descent can indeed learn the parameters accurately. A key idea underpinning our results is the design of two {\em distinct} loss functions, one for recovering the expert parameters and another for recovering the gating parameters. We demonstrate the first sample complexity results for parameter recovery in this model for any algorithm and demonstrate significant performance gains over standard loss functions in numerical experiments.

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。

↑