Errata for "Cerebro: a data system for optimized deep learning model selection"
Keyword(s):
We discovered that there was an inconsistency in the communication cost formulation for the decentralized fine-grained training method in Table 2 of our paper [1]. We used Horovod as the archetype for decentralized fine-grained approaches, and its correct communication cost is higher than what we had reported. So, we amend the communication cost of decentralized fine-grained to [EQUATION]
Keyword(s):
Keyword(s):
2021 ◽
pp. 1-13
Keyword(s):
Keyword(s):
Keyword(s):
2020 ◽
Vol 57
(1)
◽
pp. 102141
◽
Keyword(s):
Keyword(s):