TY - JOUR
T1 - Memory-efficient adaptive optimization
AU - Anil, Rohan
AU - Gupta, Vineet
AU - Koren, Tomer
AU - Singer, Yoram
N1 - Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter, thus introducing significant memory overheads that restrict the size of the model being used as well as the number of examples in a mini-batch. We describe an effective and flexible adaptive optimization method with greatly reduced memory overhead. Our method retains the benefits of per-parameter adaptivity while allowing significantly larger models and batch sizes. We give convergence guarantees for our method, and demonstrate its effectiveness in training very large translation and language models with up to 2-fold speedups compared to the state-of-the-art.
AB - Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter, thus introducing significant memory overheads that restrict the size of the model being used as well as the number of examples in a mini-batch. We describe an effective and flexible adaptive optimization method with greatly reduced memory overhead. Our method retains the benefits of per-parameter adaptivity while allowing significantly larger models and batch sizes. We give convergence guarantees for our method, and demonstrate its effectiveness in training very large translation and language models with up to 2-fold speedups compared to the state-of-the-art.
UR - http://www.scopus.com/inward/record.url?scp=85090172395&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???
AN - SCOPUS:85090172395
SN - 1049-5258
VL - 32
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019
Y2 - 8 December 2019 through 14 December 2019
ER -