Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Penney, Drew"'
Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation
Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential translation acc
Externí odkaz:
http://arxiv.org/abs/2307.01377
Autor:
Penney, Drew, Li, Bin, Chen, Lizhong, Sydir, Jaroslaw J., Drewek-Ossowicka, Anna, Illikkal, Ramesh, Tai, Charlie, Iyer, Ravi, Herdrich, Andrew
Resource sharing between multiple workloads has become a prominent practice among cloud service providers, motivated by demand for improved resource utilization and reduced cost of ownership. Effective resource sharing, however, remains an open chall
Externí odkaz:
http://arxiv.org/abs/2304.04797
Autor:
Penney, Drew, Li, Bin, Sydir, Jaroslaw, Chen, Lizhong, Tai, Charlie, Lee, Stefan, Walsh, Eoin, Long, Thomas
A growing number of service providers are exploring methods to improve server utilization and reduce power consumption by co-scheduling high-priority latency-critical workloads with best-effort workloads. This practice requires strict resource alloca
Externí odkaz:
http://arxiv.org/abs/2201.07916
Autor:
Penney, Drew D., Chen, Lizhong
Machine learning has enabled significant benefits in diverse fields, but, with a few exceptions, has had limited impact on computer architecture. Recent work, however, has explored broader applicability for design, optimization, and simulation. Notab
Externí odkaz:
http://arxiv.org/abs/1909.12373
Autor:
Penney, Drew, Li, Bin, Sydir, Jaroslaw J., Chen, Lizhong, Tai, Charlie, Lee, Stefan, Walsh, Eoin, Long, Thomas
Publikováno v:
In Future Generation Computer Systems August 2023 145:164-175
Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where conventional design
Externí odkaz:
http://arxiv.org/abs/1905.04423
Publikováno v:
Synthesis Lectures on Computer Architecture; 11/6/2020, Vol. 15 Issue 5, pix-124, 134p