Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning

Autor:	Benzing, Frederik, Gauy, Marcelo Matheus, Mujika, Asier, Martinsson, Anders, Steger, Angelika
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids learning dependencies beyond the truncation horizon. In contrast, the online training algorithm Real Time Recurrent Learning (RTRL) provides untruncated gradients, with the disadvantage of impractically large computational costs. Recently published approaches reduce these costs by providing noisy approximations of RTRL. We present a new approximation algorithm of RTRL, Optimal Kronecker-Sum Approximation (OK). We prove that OK is optimal for a class of approximations of RTRL, which includes all approaches published so far. Additionally, we show that OK has empirically negligible noise: Unlike previous algorithms it matches TBPTT in a real world task (character-level Penn TreeBank) and can exploit online parameter updates to outperform TBPTT in a synthetic string memorization task. Code availiable on github. Comment: ICML 2019 camera ready version; new version includes additional plots in the appendix
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1902.03993 Zobrazit plný text záznamu View this record from Arxiv