Semantic Scholar Open Access 2016 265 sitasi

Memory-Efficient Backpropagation Through Time

A. Gruslys R. Munos Ivo Danihelka Marc Lanctot Alex Graves

Abstrak

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of intermediate results and recomputation. The algorithm is capable of tightly fitting within almost any user-set memory budget while finding an optimal execution policy minimizing the computational cost. Computational devices have limited memory capacity and maximizing a computational performance given a fixed memory budget is a practical use-case. We provide asymptotic computational upper bounds for various regimes. The algorithm is particularly effective for long sequences. For sequences of length 1000, our algorithm saves 95\% of memory usage while using only one third more time per iteration than the standard BPTT.

Topik & Kata Kunci

Penulis (5)

A

A. Gruslys

R

R. Munos

I

Ivo Danihelka

M

Marc Lanctot

A

Alex Graves

Format Sitasi

Gruslys, A., Munos, R., Danihelka, I., Lanctot, M., Graves, A. (2016). Memory-Efficient Backpropagation Through Time. https://www.semanticscholar.org/paper/f61e9fd5a4878e1493f7a6b03774a61c17b7e9a4

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2016
Bahasa
en
Total Sitasi
265×
Sumber Database
Semantic Scholar
Akses
Open Access ✓