{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T16:26:50Z","timestamp":1756571210783,"version":"3.41.0"},"reference-count":23,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGOPS Oper. Syst. Rev."],"published-print":{"date-parts":[[2019,7,25]]},"abstract":"<jats:p>Deploying machine learning into IoT cloud settings will require an evolution of the cloud infrastructure. In this white paper, we justify this assertion and identify new capabilities needed for real-time intelligent systems. We also outline our initial efforts to create a new edge architecture more suitable for ML. Although the work is still underway, several components exist, and we review them. We then point to open technical problems that will need to be solved as we progress further in this direction.<\/jats:p>","DOI":"10.1145\/3352020.3352023","type":"journal-article","created":{"date-parts":[[2019,7,26]],"date-time":"2019-07-26T13:17:18Z","timestamp":1564147038000},"page":"7-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Cloud-Hosted Intelligence for Real-time IoT Applications"],"prefix":"10.1145","volume":"53","author":[{"given":"Ken","family":"Birman","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bharath","family":"Hariharan","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"De Sa","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Abadi M. Barham P. Chen J. Chen Z. Davis A. Dean J. Devin M. Ghemawat S. Irving G. Isard M. Kudlur M. Levenberg J. Monga R. Moore S. Murray D. G. Steiner B. Tucker P. Vasudevan V. Warden P. Wicke M. Yu Y. and Zheng X. Tensorflow: A system for large-scale machine learning.   Abadi M. Barham P. Chen J. Chen Z. Davis A. Dean J. Devin M. Ghemawat S. Irving G. Isard M. Kudlur M. Levenberg J. Monga R. Moore S. Murray D. G. Steiner B. Tucker P. Vasudevan V. Warden P. Wicke M. Yu Y. and Zheng X. Tensorflow: A system for large-scale machine learning."},{"key":"e_1_2_1_2_1","volume-title":"Distributed learning with sublinear communication. arXiv preprint arXiv:1902.11259","author":"Acharya J.","year":"2019","unstructured":"Acharya , J. , De Sa , C. , Foster , D. J. , and Sridharan , K . Distributed learning with sublinear communication. arXiv preprint arXiv:1902.11259 ( 2019 ). Acharya, J., De Sa, C., Foster, D. J., and Sridharan, K. Distributed learning with sublinear communication. arXiv preprint arXiv:1902.11259 (2019)."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2898607.2898816"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"e_1_2_1_6_1","volume-title":"Minibatch gibbs sampling on large graphical models. arXiv preprint arXiv:1806.06086","author":"De Sa C.","year":"2018","unstructured":"De Sa , C. , Chen , V. , and Wong , W . Minibatch gibbs sampling on large graphical models. arXiv preprint arXiv:1806.06086 ( 2018 ). De Sa, C., Chen, V., and Wong, W. Minibatch gibbs sampling on large graphical models. arXiv preprint arXiv:1806.06086 (2018)."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"e_1_2_1_8_1","first-page":"1567","volume-title":"JMLR workshop and conference proceedings","volume":"48","author":"De Sa C.","year":"2016","unstructured":"De Sa , C. , Olukotun , K. , and R\u00b4e , C . Ensuring rapid mixing and low bias for asynchronous gibbs sampling . In JMLR workshop and conference proceedings ( 2016 ), vol. 48 , NIH Public Access , p. 1567 . De Sa, C., Olukotun, K., and R\u00b4e, C. Ensuring rapid mixing and low bias for asynchronous gibbs sampling. In JMLR workshop and conference proceedings (2016), vol. 48, NIH Public Access, p. 1567."},{"key":"e_1_2_1_9_1","volume-title":"ICML","author":"Finn C.","year":"2017","unstructured":"Finn , C. , Abbeel , P. , and Levine , S . Model-agnostic meta-learning for fast adaptation of deep networks . In ICML ( 2017 ). Finn, C., Abbeel, P., and Levine, S. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML (2017)."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.328"},{"key":"e_1_2_1_11_1","first-page":"1","volume-title":"Advances in neural information processing systems","author":"He B. D.","year":"2016","unstructured":"He , B. D. , De Sa , C. M. , Mitliagkas , I. , and R\u00b4e , C . Scan order in gibbs sampling: Models in which it matters and bounds on how much . In Advances in neural information processing systems ( 2016 ), pp. 1 -- 9 . He, B. D., De Sa, C. M., Mitliagkas, I., and R\u00b4e, C. Scan order in gibbs sampling: Models in which it matters and bounds on how much. In Advances in neural information processing systems (2016), pp. 1--9."},{"key":"e_1_2_1_12_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard A. G.","year":"2017","unstructured":"Howard , A. G. , Zhu , M. , Chen , B. , Kalenichenko , D. , Wang , W. , Weyand , T. , Andreetto , M. , and Adam , H . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 ( 2017 ). Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302258"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812806"},{"key":"e_1_2_1_16_1","volume-title":"Sysml: The new frontier of machine learning systems. https:\/\/www.sysml. cc\/doc\/sysml-whitepaper.pdf","author":"Ratner A.","year":"2019","unstructured":"Ratner , A. , Alistarh , D. , Alonso , G. , Andersen , D. G. , Bailis , P. , Bird , S. , Carlini , N. , Catanzaro , B. , Chayes , J. , Chung , E. , Dally , B. , De Sa , C. , Dean , J. , Dhillon , I. S. , Dimakis , A. , Dubey , P. , Elkan , C. , Fursin , G. , Ganger , G. R. , Getoor , L. , Gibbons , P. B. , Gibson , G. A. , Gonzalez , J. E. , Gottschlich , J. , Han , S. , Hazelwood , K. , Huang , F. , Jaggi , M. , Jamieson , K. , Jordan , M. I. , Joshi , G. , Khalaf , R. , Knight , J. , Konecn\u00b4y , J. , Kraska , T. , Kumar , A. , Kyrillidis , A. , Lakshmiratan , A. , Li , J. , Madden , S. , McMahan , H. B. , Meijer , E. , Mitliagkas , I. , Monga , R. , Murray , D. , Olukotun , K. , Papailiopoulos , D. , Pekhimenko , G. , R'e , C. , Rekatsinas , T. , Rostamizadeh , A. , Sedghi , H. , Sen , S. , Smith , V. , Smola , A. , Song , D. , Sparks , E. , Stoica , I. , Sze , V. , Udell , M. , Vanschoren , J. , Venkataraman , S. , Vinayak , R. , Weimer , M. , Wilson , A. G. , Xing , E. , Zaharia , M. , Zhang , C. , and Talwalkar , A . Sysml: The new frontier of machine learning systems. https:\/\/www.sysml. cc\/doc\/sysml-whitepaper.pdf , 2019 . Ratner, A., Alistarh, D., Alonso, G., Andersen, D. G., Bailis, P., Bird, S., Carlini, N., Catanzaro, B., Chayes, J., Chung, E., Dally, B., De Sa, C., Dean, J., Dhillon, I. S., Dimakis, A., Dubey, P., Elkan, C., Fursin, G., Ganger, G. R., Getoor, L., Gibbons, P. B., Gibson, G. A., Gonzalez, J. E., Gottschlich, J., Han, S., Hazelwood, K., Huang, F., Jaggi, M., Jamieson, K., Jordan, M. I., Joshi, G., Khalaf, R., Knight, J., Konecn\u00b4y, J., Kraska, T., Kumar, A., Kyrillidis, A., Lakshmiratan, A., Li, J., Madden, S., McMahan, H. B., Meijer, E., Mitliagkas, I., Monga, R., Murray, D., Olukotun, K., Papailiopoulos, D., Pekhimenko, G., R'e, C., Rekatsinas, T., Rostamizadeh, A., Sedghi, H., Sen, S., Smith, V., Smola, A., Song, D., Sparks, E., Stoica, I., Sze, V., Udell, M., Vanschoren, J., Venkataraman, S., Vinayak, R., Weimer, M.,Wilson, A. G., Xing, E., Zaharia, M., Zhang, C., and Talwalkar, A. Sysml: The new frontier of machine learning systems. https:\/\/www.sysml. cc\/doc\/sysml-whitepaper.pdf, 2019."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_1_18_1","volume-title":"NIPS","author":"Snell J.","year":"2017","unstructured":"Snell , J. , Swersky , K. , and Zemel , R. S . Prototypical networks for few-shot learning . In NIPS ( 2017 ). Snell, J., Swersky, K., and Zemel, R. S. Prototypical networks for few-shot learning. In NIPS (2017)."},{"key":"e_1_2_1_19_1","volume-title":"D. Matching networks for one shot learning. In NIPS.","author":"Vinyals O.","year":"2016","unstructured":"Vinyals , O. , Blundell , C. , Lillicrap , T. , kavukcuoglu, k., and Wierstra , D. Matching networks for one shot learning. In NIPS. 2016 . Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., and Wierstra, D. Matching networks for one shot learning. In NIPS. 2016."},{"key":"e_1_2_1_20_1","volume-title":"Computer Vision and Pattern Recognition (CVPR)","author":"Wang Y.-X.","year":"2018","unstructured":"Wang , Y.-X. , Girshick , R. , Herbert , M. , and Hariharan , B . Low-shot learning from imaginary data . In Computer Vision and Pattern Recognition (CVPR) ( 2018 ). Wang, Y.-X., Girshick, R., Herbert, M., and Hariharan, B. Low-shot learning from imaginary data. In Computer Vision and Pattern Recognition (CVPR) (2018)."},{"key":"e_1_2_1_21_1","volume-title":"Computer Vision and Pattern Recognition (CVPR)","author":"Wertheimer D.","year":"2019","unstructured":"Wertheimer , D. , and Hariharan , B . Few-shot learning with localization in realistic settings . In Computer Vision and Pattern Recognition (CVPR) ( 2019 ). Wertheimer, D., and Hariharan, B. Few-shot learning with localization in realistic settings. In Computer Vision and Pattern Recognition (CVPR) (2019)."},{"key":"e_1_2_1_22_1","volume-title":"Building efficient deep neural networks with unitary group convolutions. arXiv preprint arXiv:1811.07755","author":"Zhao R.","year":"2018","unstructured":"Zhao , R. , Hu , Y. , Dotzel , J. , De Sa , C. , and Zhang , Z . Building efficient deep neural networks with unitary group convolutions. arXiv preprint arXiv:1811.07755 ( 2018 ). Zhao, R., Hu, Y., Dotzel, J., De Sa, C., and Zhang, Z. Building efficient deep neural networks with unitary group convolutions. arXiv preprint arXiv:1811.07755 (2018)."},{"key":"e_1_2_1_23_1","volume-title":"Improving neural network quantization without retraining using outlier channel splitting. CoRR abs\/1901.09504","author":"Zhao R.","year":"2019","unstructured":"Zhao , R. , Hu , Y. , Dotzel , J. , Sa , C. D. , and Zhang , Z . Improving neural network quantization without retraining using outlier channel splitting. CoRR abs\/1901.09504 ( 2019 ). Zhao, R., Hu, Y., Dotzel, J., Sa, C. D., and Zhang, Z. Improving neural network quantization without retraining using outlier channel splitting. CoRR abs\/1901.09504 (2019)."}],"container-title":["ACM SIGOPS Operating Systems Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352020.3352023","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3352020.3352023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:26:15Z","timestamp":1750206375000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352020.3352023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,7,25]]}},"alternative-id":["10.1145\/3352020.3352023"],"URL":"https:\/\/doi.org\/10.1145\/3352020.3352023","relation":{},"ISSN":["0163-5980"],"issn-type":[{"type":"print","value":"0163-5980"}],"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"2019-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}