A
Ashish Agarwal
Researcher at Google
Publications - 20
Citations - 11426
Ashish Agarwal is an academic researcher from Google. The author has contributed to research in topics: Taylor series & Axiom. The author has an hindex of 11, co-authored 18 publications receiving 10052 citations. Previous affiliations of Ashish Agarwal include University of Illinois at Urbana–Champaign.
Papers
More filters
Posted Content
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martín Abadi,Ashish Agarwal,Paul Barham,Eugene Brevdo,Zhifeng Chen,Craig Citro,Greg S. Corrado,Andy Davis,Jeffrey Dean,Matthieu Devin,Sanjay Ghemawat,Ian Goodfellow,Andrew Harp,Geoffrey Irving,Michael Isard,Yangqing Jia,Rafal Jozefowicz,Lukasz Kaiser,Manjunath Kudlur,Josh Levenberg,Dan Mané,Rajat Monga,Sherry Moore,Derek G. Murray,Chris Olah,Mike Schuster,Jonathon Shlens,Benoit Steiner,Ilya Sutskever,Kunal Talwar,Paul A. Tucker,Vincent Vanhoucke,Vijay K. Vasudevan,Fernanda B. Viégas,Oriol Vinyals,Pete Warden,Martin Wattenberg,Martin Wicke,Yuan Yu,Xiaoqiang Zheng +39 more
TL;DR: The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields.
Proceedings ArticleDOI
Overlapping experiment infrastructure: more, better, faster experimentation
TL;DR: Google's overlapping experiment infrastructure is described, and the associated tools and educational processes required to use it effectively are discussed, which can be generalized and applied by any entity interested in using experimentation to improve search engines and other web applications.
Journal ArticleDOI
Capacity bounds for ad hoc and hybrid wireless networks
Ashish Agarwal,P. R. Kumar +1 more
TL;DR: It is shown that the aggregate throughput capacity, measured as the sum of individual throughputs, can scale linearly in the number of nodes and underscores the importance of choosing minimum power levels for communication and suggests that simply communicating with the closest node or base station could yield good capacity even for multihop hybrid wireless networks.
Hallucinations in Neural Machine Translation
TL;DR: It is shown that NMT systems are susceptible to producing highly pathological translations that are completely untethered from the source material, which is term hallucinations.
Journal ArticleDOI
Improved capacity bounds for wireless networks
Ashish Agarwal,P. R. Kumar +1 more
TL;DR: Improved upper and lower bounds are obtained on the best case and random case transport capacities of wireless networks under the Protocol Model of communication in Reference.