Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Joosen, Artjom"'
Autor:
Darlow, Luke, Deng, Qiwen, Hassan, Ahmed, Asenov, Martin, Singh, Rajkarn, Joosen, Artjom, Barker, Adam, Storkey, Amos
It is challenging to scale time series forecasting models such that they forecast accurately for multiple distinct domains and datasets, all with potentially different underlying collection procedures (e.g., sample resolution), patterns (e.g., period
Externí odkaz:
http://arxiv.org/abs/2407.17880
Autor:
Joosen, Artjom, Hassan, Ahmed, Asenov, Martin, Singh, Rajkarn, Darlow, Luke, Wang, Jianfeng, Barker, Adam
Publikováno v:
SoCC '23: Proceedings of the 2023 ACM Symposium on Cloud Computing, October 2023, Pages 443-458
This paper releases and analyzes two new Huawei cloud serverless traces. The traces span a period of over 7 months with over 1.4 trillion function invocations combined. The first trace is derived from Huawei's internal workloads and contains detailed
Externí odkaz:
http://arxiv.org/abs/2312.10127
Autor:
He, Peiyang, Griffin, Charlie, Kacprzyk, Krzysztof, Joosen, Artjom, Collyer, Michael, Shtedritski, Aleksandar, Asano, Yuki M.
Privacy considerations and bias in datasets are quickly becoming high-priority issues that the computer vision community needs to face. So far, little attention has been given to practical solutions that do not involve collection of new datasets. In
Externí odkaz:
http://arxiv.org/abs/2103.06587