arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.02201cs.LG
收藏

关于RNNs表达能力中深度的作用

On the Role of Depth in the Expressivity of RNNs

Mila & DIRO(Mila与DIRO);Université de Montréal(蒙特利尔大学);CIFAR AI Chair(CIFAR AI主席)

Maude Lizaire, Michael Rizvi-Martel, Éric Dupuis, Guillaume Rabusseau

AI总结:

研究探讨了RNNs深度如何通过提升记忆容量和输入转换复杂性增强表达能力,分析了2RNNs的多项式变换特性,并验证了乘法交互无法被逐层非线性替代。

摘要:

feedforward神经网络中深度的优势已广为人知:通过多个线性变换层与非线性激活的组合可实现复杂计算。尽管在循环神经网络(RNNs)中预期有类似效果,但深度如何与递归相互作用以塑造表达能力仍不清楚。本文正式证明深度能高效提升RNNs的记忆容量,从而通过允许更复杂的输入转换和改善过去信息的保留来增强表达能力。我们进一步将分析扩展到2RNNs,即一种具有输入与隐藏状态之间乘法交互的RNNs泛化形式。不同于RNNs在无非线性激活时保持线性,2RNNs执行多项式变换,其最大次数随深度增长。我们进一步证明乘法交互一般不能被逐层非线性替代。最后,我们在合成和现实任务上验证了这些见解。

英文摘要:

The benefits of depth in feedforward neural networks are well known: composing multiple layers of linear transformations with nonlinear activations enables complex computations. While similar effects are expected in recurrent neural networks (RNNs), it remains unclear how depth interacts with recurrence to shape expressive power. Here, we formally show that depth increases RNNs' memory capacity efficiently with respect to the number of parameters, thus enhancing expressivity both by enabling more complex input transformations and improving the retention of past information. We broaden our analysis to 2RNNs, a generalization of RNNs with multiplicative interactions between inputs and hidden states. Unlike RNNs, which remain linear without nonlinear activations, 2RNNs perform polynomial transformations whose maximal degree grows with depth. We further show that multiplicative interactions cannot, in general, be replaced by layerwise nonlinearities. Finally, we validate these insights empirically on synthetic and real-world tasks.

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。

↑