{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:35:24Z","timestamp":1730201724810,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/cahpc.2018.8645861","type":"proceedings-article","created":{"date-parts":[[2019,2,21]],"date-time":"2019-02-21T18:19:26Z","timestamp":1550773166000},"page":"298-305","source":"Crossref","is-referenced-by-count":2,"title":["Accelerating Deep Neural Network Training for Action Recognition on a Cluster of GPUs"],"prefix":"10.1109","author":[{"given":"Guojing","family":"Cong","sequence":"first","affiliation":[]},{"given":"Giacomo","family":"Domeniconi","sequence":"additional","affiliation":[]},{"given":"Joshua","family":"Shapiro","sequence":"additional","affiliation":[]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Barry","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageN et classification with deep convolutional neural networks","volume":"60","author":"krizhevsky","year":"2017","journal-title":"Commun ACM"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33374-3_41"},{"key":"ref13","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)"},{"key":"ref14","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Advances in neural information processing systems"},{"journal-title":"Gpu asynchronous stochastic gradient descent to speed up neural network training","year":"2013","author":"paine","key":"ref15"},{"key":"ref16","article-title":"On sampling rates in simulation-based recursions","author":"pasupathy","year":"2017","journal-title":"SIAM Journal of Optimization"},{"journal-title":"On Automatic Differentiation","year":"2017","author":"paszke","key":"ref17"},{"key":"ref18","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"You only look once: Unified, real-time object detection","volume":"abs 1506 2640","author":"redmon","year":"2015","journal-title":"CoRR"},{"key":"ref28","first-page":"1701","article-title":"Asynchronous distributed admm for consensus optimization","author":"zhang","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML 2014)"},{"key":"ref4","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)"},{"key":"ref27","article-title":"Scaling SGD batch size to 32k for imagenet training","volume":"abs 1708 3888","author":"you","year":"2017","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"dekel","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","first-page":"685","article-title":"Deep learning with elastic averaging SGD","author":"zhang","year":"2015","journal-title":"Advances in Neural Information Processing Systems 28 Annual Conference on Neural Information Processing Systems 2015"},{"key":"ref5","first-page":"1223","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Accurate, large minibatch SGD: training imagenet in 1 hour","volume":"abs 1706 2677","author":"goyal","year":"2017","journal-title":"CoRR"},{"journal-title":"Optimization Methods for Large-Scale Machine Learning","year":"2017","author":"bottou","key":"ref2"},{"key":"ref9","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 ICML'15"},{"key":"ref1","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref20","article-title":"Imagenet large scale visual recognition challenge","volume":"abs 1409 575","author":"russakovsky","year":"2014","journal-title":"CoRR"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref21","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref23","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"abs 1212 402","author":"soomro","year":"2012","journal-title":"CoRR"},{"key":"ref26","article-title":"Rethinking spatiotemporal feature learning for video understanding","volume":"abs 1712 4851","author":"xie","year":"2017","journal-title":"CoRR"},{"key":"ref25","article-title":"Towards good practices for very deep two-stream convnets","volume":"abs 1507 2159","author":"wang","year":"2015","journal-title":"CoRR"}],"event":{"name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","start":{"date-parts":[[2018,9,24]]},"location":"Lyon, France","end":{"date-parts":[[2018,9,27]]}},"container-title":["2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8638685\/8645847\/08645861.pdf?arnumber=8645861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T21:21:06Z","timestamp":1552944066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8645861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/cahpc.2018.8645861","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}