{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T07:11:25Z","timestamp":1760425885970,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJCR19F5"],"award-info":[{"award-number":["JPMJCR19F5"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,8,23]]},"DOI":"10.1145\/3394486.3403265","type":"proceedings-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T23:04:00Z","timestamp":1597964640000},"page":"2145-2153","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Rich Information is Affordable: A Systematic Performance Analysis of Second-order Optimization Using K-FAC"],"prefix":"10.1145","author":[{"given":"Yuichiro","family":"Ueno","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology & AIST-Tokyo Tech RWBC-OIL, AIST, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuki","family":"Osawa","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yohei","family":"Tsuji","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Naruse","sequence":"additional","affiliation":[{"name":"NVIDIA, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rio","family":"Yokota","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology & AIST-Tokyo Tech RWBC-OIL, AIST, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes. arXiv:1711.04325 [cs] (Nov","author":"Akiba Takuya","year":"2017","unstructured":"Takuya Akiba , Shuji Suzuki , and Keisuke Fukuda . 2017. Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes. arXiv:1711.04325 [cs] (Nov . 2017 ). http:\/\/arxiv.org\/abs\/1711.04325 Takuya Akiba, Shuji Suzuki, and Keisuke Fukuda. 2017. Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes. arXiv:1711.04325 [cs] (Nov. 2017). http:\/\/arxiv.org\/abs\/1711.04325"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning -","volume":"70","author":"Botev Aleksandar","year":"2017","unstructured":"Aleksandar Botev , Hippolyt Ritter , and David Barber . 2017 . Practical Gauss-Newton optimisation for deep learning . In Proceedings of the 34th International Conference on Machine Learning - Volume 70 (ICML'17). JMLR.org, Sydney, NSW, Australia, 557--565. Aleksandar Botev, Hippolyt Ritter, and David Barber. 2017. Practical Gauss-Newton optimisation for deep learning. In Proceedings of the 34th International Conference on Machine Learning - Volume 70 (ICML'17). JMLR.org, Sydney, NSW, Australia, 557--565."},{"key":"e_1_3_2_1_4_1","volume-title":"BackPACK: Packing more into backprop. arXiv:1912.10985 [cs, stat] (Dec","author":"Dangel Felix","year":"2019","unstructured":"Felix Dangel , Frederik Kunstner , and Philipp Hennig . 2019. BackPACK: Packing more into backprop. arXiv:1912.10985 [cs, stat] (Dec . 2019 ). http:\/\/arxiv.org\/abs\/1912.10985 Felix Dangel, Frederik Kunstner, and Philipp Hennig. 2019. BackPACK: Packing more into backprop. arXiv:1912.10985 [cs, stat] (Dec. 2019). http:\/\/arxiv.org\/abs\/1912.10985"},{"key":"e_1_3_2_1_5_1","volume-title":"Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv:1706.02677 [cs] (June","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal , Piotr Doll\u00e1r , Ross Girshick , Pieter Noordhuis , Lukasz Wesolowski , Aapo Kyrola , Andrew Tulloch , Yangqing Jia , and Kaiming He. 2017. Accurate , Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv:1706.02677 [cs] (June 2017 ). http:\/\/arxiv.org\/abs\/1706.02677 Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, and Kaiming He. 2017. Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv:1706.02677 [cs] (June 2017). http:\/\/arxiv.org\/abs\/1706.02677"},{"key":"e_1_3_2_1_6_1","volume-title":"A Kronecker-factored approximate Fisher matrix for convolution layers. arXiv:1602.01407 [cs, stat] (May","author":"Grosse Roger","year":"2016","unstructured":"Roger Grosse and James Martens . 2016. A Kronecker-factored approximate Fisher matrix for convolution layers. arXiv:1602.01407 [cs, stat] (May 2016 ). http:\/\/arxiv.org\/abs\/1602.01407 Roger Grosse and James Martens. 2016. A Kronecker-factored approximate Fisher matrix for convolution layers. arXiv:1602.01407 [cs, stat] (May 2016). http:\/\/arxiv.org\/abs\/1602.01407"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778","author":"He K.","year":"2016","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun . 2016 . Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778 . https:\/\/doi.org\/10.1109\/CVPR. 2016 .90 10.1109\/CVPR.2016.90 K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778. https:\/\/doi.org\/10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","volume-title":"Bag of Tricks for Image Classification with Convolutional Neural Networks. arXiv:1812.01187 [cs] (Dec","author":"He Tong","year":"2018","unstructured":"Tong He , Zhi Zhang , Hang Zhang , Zhongyue Zhang , Junyuan Xie , and Mu Li. 2018. Bag of Tricks for Image Classification with Convolutional Neural Networks. arXiv:1812.01187 [cs] (Dec . 2018 ). http:\/\/arxiv.org\/abs\/1812.01187 Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. 2018. Bag of Tricks for Image Classification with Convolutional Neural Networks. arXiv:1812.01187 [cs] (Dec. 2018). http:\/\/arxiv.org\/abs\/1812.01187"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00052"},{"key":"e_1_3_2_1_10_1","volume-title":"Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes. arXiv:1807.11205 [cs, stat] (July","author":"Jia Xianyan","year":"2018","unstructured":"Xianyan Jia , Shutao Song , Wei He , Yangzihao Wang , Haidong Rong , Feihu Zhou , Liqiang Xie , Zhenyu Guo , Yuanzhou Yang , Liwei Yu , Tiegang Chen , Guangxiao Hu , Shaohuai Shi , and Xiaowen Chu . 2018. Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes. arXiv:1807.11205 [cs, stat] (July 2018 ). http:\/\/arxiv.org\/abs\/1807.11205 Xianyan Jia, Shutao Song, Wei He, Yangzihao Wang, Haidong Rong, Feihu Zhou, Liqiang Xie, Zhenyu Guo, Yuanzhou Yang, Liwei Yu, Tiegang Chen, Guangxiao Hu, Shaohuai Shi, and Xiaowen Chu. 2018. Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes. arXiv:1807.11205 [cs, stat] (July 2018). http:\/\/arxiv.org\/abs\/1807.11205"},{"key":"e_1_3_2_1_11_1","volume-title":"Restructuring Batch Normalization to Accelerate CNN Training. arXiv:1807.01702 [cs] (July","author":"Jung Wonkyung","year":"2018","unstructured":"Wonkyung Jung , Daejin Jung , and Byeongho Kim , Sunjung Lee , Wonjong Rhee , and Jung Ho Ahn . 2018. Restructuring Batch Normalization to Accelerate CNN Training. arXiv:1807.01702 [cs] (July 2018 ). http:\/\/arxiv.org\/abs\/1807.01702 Wonkyung Jung, Daejin Jung, and Byeongho Kim, Sunjung Lee, Wonjong Rhee, and Jung Ho Ahn. 2018. Restructuring Batch Normalization to Accelerate CNN Training. arXiv:1807.01702 [cs] (July 2018). http:\/\/arxiv.org\/abs\/1807.01702"},{"key":"e_1_3_2_1_12_1","volume-title":"Overcoming catastrophic forgetting in neural networks. arXiv:1612.00796 [cs, stat] (Jan","author":"Kirkpatrick James","year":"2017","unstructured":"James Kirkpatrick , Razvan Pascanu , Neil Rabinowitz , Joel Veness , Guillaume Desjardins , Andrei A. Rusu , Kieran Milan , John Quan , Tiago Ramalho , Agnieszka Grabska-Barwinska , Demis Hassabis , Claudia Clopath , Dharshan Kumaran , and Raia Hadsell . 2017. Overcoming catastrophic forgetting in neural networks. arXiv:1612.00796 [cs, stat] (Jan . 2017 ). http:\/\/arxiv.org\/abs\/1612.00796 James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell. 2017. Overcoming catastrophic forgetting in neural networks. arXiv:1612.00796 [cs, stat] (Jan. 2017). http:\/\/arxiv.org\/abs\/1612.00796"},{"key":"e_1_3_2_1_13_1","volume-title":"Limitations of the Empirical Fisher Approximation for Natural Gradient Descent. arXiv:1905.12558 [cs, stat] (Dec","author":"Kunstner Frederik","year":"2019","unstructured":"Frederik Kunstner , Lukas Balles , and Philipp Hennig . 2019. Limitations of the Empirical Fisher Approximation for Natural Gradient Descent. arXiv:1905.12558 [cs, stat] (Dec . 2019 ). http:\/\/arxiv.org\/abs\/1905.12558 Frederik Kunstner, Lukas Balles, and Philipp Hennig. 2019. Limitations of the Empirical Fisher Approximation for Natural Gradient Descent. arXiv:1905.12558 [cs, stat] (Dec. 2019). http:\/\/arxiv.org\/abs\/1905.12558"},{"key":"e_1_3_2_1_14_1","volume-title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature. arXiv:1503.05671 [cs, stat] (March","author":"Martens James","year":"2015","unstructured":"James Martens and Roger Grosse . 2015. Optimizing Neural Networks with Kronecker-factored Approximate Curvature. arXiv:1503.05671 [cs, stat] (March 2015 ). http:\/\/arxiv.org\/abs\/1503.05671 James Martens and Roger Grosse. 2015. Optimizing Neural Networks with Kronecker-factored Approximate Curvature. arXiv:1503.05671 [cs, stat] (March 2015). http:\/\/arxiv.org\/abs\/1503.05671"},{"key":"e_1_3_2_1_15_1","volume-title":"An Empirical Model of Large-Batch Training. arXiv:1812.06162 [cs, stat] (Dec","author":"McCandlish Sam","year":"2018","unstructured":"Sam McCandlish , Jared Kaplan , Dario Amodei , and Open AI Dota Team . 2018. An Empirical Model of Large-Batch Training. arXiv:1812.06162 [cs, stat] (Dec . 2018 ). http:\/\/arxiv.org\/abs\/1812.06162 Sam McCandlish, Jared Kaplan, Dario Amodei, and OpenAI Dota Team. 2018. An Empirical Model of Large-Batch Training. arXiv:1812.06162 [cs, stat] (Dec. 2018). http:\/\/arxiv.org\/abs\/1812.06162"},{"key":"e_1_3_2_1_16_1","volume-title":"Mixed Precision Training. arXiv:1710.03740 [cs, stat] (Feb","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius , Sharan Narang , Jonah Alben , Gregory Diamos , Erich Elsen , David Garcia , Boris Ginsburg , Michael Houston , Oleksii Kuchaiev , Ganesh Venkatesh , and Hao Wu. 2018. Mixed Precision Training. arXiv:1710.03740 [cs, stat] (Feb . 2018 ). http:\/\/arxiv.org\/abs\/1710.03740 Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed Precision Training. arXiv:1710.03740 [cs, stat] (Feb. 2018). http:\/\/arxiv.org\/abs\/1710.03740"},{"key":"e_1_3_2_1_17_1","unstructured":"Hiroaki Mikami Hisahiro Suganuma Pongsakorn U-chupala Yoshiki Tanaka and Yuichi Kageyama. 2018. ImageNet\/ResNet-50 Training in 224 Seconds. (Nov. 2018). https:\/\/arxiv.org\/abs\/1811.05233  Hiroaki Mikami Hisahiro Suganuma Pongsakorn U-chupala Yoshiki Tanaka and Yuichi Kageyama. 2018. ImageNet\/ResNet-50 Training in 224 Seconds. (Nov. 2018). https:\/\/arxiv.org\/abs\/1811.05233"},{"key":"e_1_3_2_1_18_1","volume-title":"Scalable and Practical Natural Gradient for Large-Scale Deep Learning. arXiv:2002.06015 [cs, stat] (Feb","author":"Osawa Kazuki","year":"2020","unstructured":"Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Chuan-Sheng Foo , and Rio Yokota . 2020. Scalable and Practical Natural Gradient for Large-Scale Deep Learning. arXiv:2002.06015 [cs, stat] (Feb . 2020 ). http:\/\/arxiv.org\/abs\/2002.06015 Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, and Rio Yokota. 2020. Scalable and Practical Natural Gradient for Large-Scale Deep Learning. arXiv:2002.06015 [cs, stat] (Feb. 2020). http:\/\/arxiv.org\/abs\/2002.06015"},{"key":"#cr-split#-e_1_3_2_1_19_1.1","doi-asserted-by":"crossref","unstructured":"Kazuki Osawa Yohei Tsuji Yuichiro Ueno Akira Naruse Rio Yokota and Satoshi Matsuoka. 2019. Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12351--12359. https:\/\/doi.org\/10.1109\/CVPR.2019.01264 10.1109\/CVPR.2019.01264","DOI":"10.1109\/CVPR.2019.01264"},{"key":"#cr-split#-e_1_3_2_1_19_1.2","doi-asserted-by":"crossref","unstructured":"Kazuki Osawa Yohei Tsuji Yuichiro Ueno Akira Naruse Rio Yokota and Satoshi Matsuoka. 2019. Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12351--12359. https:\/\/doi.org\/10.1109\/CVPR.2019.01264","DOI":"10.1109\/CVPR.2019.01264"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_22_1","volume-title":"Information matrices and generalization. arXiv:1906.07774 [cs, stat] (June","author":"Thomas Valentin","year":"2019","unstructured":"Valentin Thomas , Fabian Pedregosa , Bart van Merri\u00ebnboer , Pierre-Antoine Mangazol , Yoshua Bengio , and Nicolas Le Roux . 2019. Information matrices and generalization. arXiv:1906.07774 [cs, stat] (June 2019 ). http:\/\/arxiv.org\/abs\/1906.07774 Valentin Thomas, Fabian Pedregosa, Bart van Merri\u00ebnboer, Pierre-Antoine Mangazol, Yoshua Bengio, and Nicolas Le Roux. 2019. Information matrices and generalization. arXiv:1906.07774 [cs, stat] (June 2019). http:\/\/arxiv.org\/abs\/1906.07774"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339186.3339202"},{"key":"e_1_3_2_1_24_1","volume-title":"Exhaustive Study of Hierarchical AllReduce Patterns for Large Messages Between GPUs. In 2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). 430--439","author":"Ueno Yuichiro","year":"2019","unstructured":"Yuichiro Ueno and Rio Yokota . 2019 . Exhaustive Study of Hierarchical AllReduce Patterns for Large Messages Between GPUs. In 2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). 430--439 . https:\/\/doi.org\/10.1109\/CCGRID.2019.00057 10.1109\/CCGRID.2019.00057 Yuichiro Ueno and Rio Yokota. 2019. Exhaustive Study of Hierarchical AllReduce Patterns for Large Messages Between GPUs. In 2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). 430--439. https:\/\/doi.org\/10.1109\/CCGRID.2019.00057"},{"key":"e_1_3_2_1_25_1","volume-title":"arXiv:1706.03762 [cs] (June","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention Is All You Need. arXiv:1706.03762 [cs] (June 2017 ). http:\/\/arxiv.org\/abs\/1706.03762 Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. arXiv:1706.03762 [cs] (June 2017). http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_26_1","volume-title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis. arXiv:1905.05934 [cs, stat] (May","author":"Wang Chaoqi","year":"2019","unstructured":"Chaoqi Wang , Roger Grosse , Sanja Fidler , and Guodong Zhang . 2019. EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis. arXiv:1905.05934 [cs, stat] (May 2019 ). http:\/\/arxiv.org\/abs\/1905.05934 Chaoqi Wang, Roger Grosse, Sanja Fidler, and Guodong Zhang. 2019. EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis. arXiv:1905.05934 [cs, stat] (May 2019). http:\/\/arxiv.org\/abs\/1905.05934"},{"key":"e_1_3_2_1_27_1","volume-title":"Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds. arXiv:1903.12650 [cs, stat] (March","author":"Yamazaki Masafumi","year":"2019","unstructured":"Masafumi Yamazaki , Akihiko Kasagi , Akihiro Tabuchi , Takumi Honda , Masahiro Miwa , Naoto Fukumoto , Tsuguchika Tabaru , Atsushi Ike , and Kohta Nakashima . 2019. Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds. arXiv:1903.12650 [cs, stat] (March 2019 ). http:\/\/arxiv.org\/abs\/1903.12650 Masafumi Yamazaki, Akihiko Kasagi, Akihiro Tabuchi, Takumi Honda, Masahiro Miwa, Naoto Fukumoto, Tsuguchika Tabaru, Atsushi Ike, and Kohta Nakashima. 2019. Yet Another Accelerated SGD: ResNet-50 Training on ImageNet in 74.7 seconds. arXiv:1903.12650 [cs, stat] (March 2019). http:\/\/arxiv.org\/abs\/1903.12650"},{"key":"e_1_3_2_1_28_1","volume-title":"Image Classification at Supercomputer Scale. arXiv:1811.06992 [cs, stat] (Nov","author":"Ying Chris","year":"2018","unstructured":"Chris Ying , Sameer Kumar , Dehao Chen , Tao Wang , and Youlong Cheng . 2018. Image Classification at Supercomputer Scale. arXiv:1811.06992 [cs, stat] (Nov . 2018 ). http:\/\/arxiv.org\/abs\/1811.06992 Chris Ying, Sameer Kumar, Dehao Chen, Tao Wang, and Youlong Cheng. 2018. Image Classification at Supercomputer Scale. arXiv:1811.06992 [cs, stat] (Nov. 2018). http:\/\/arxiv.org\/abs\/1811.06992"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"e_1_3_2_1_30_1","volume-title":"mixup: Beyond Empirical Risk Minimization. arXiv:1710.09412 [cs, stat] (April","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang , Moustapha Cisse , Yann N. Dauphin , and David Lopez-Paz . 2018. mixup: Beyond Empirical Risk Minimization. arXiv:1710.09412 [cs, stat] (April 2018 ). http:\/\/arxiv.org\/abs\/1710.09412 Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. arXiv:1710.09412 [cs, stat] (April 2018). http:\/\/arxiv.org\/abs\/1710.09412"}],"event":{"name":"KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Virtual Event CA USA","acronym":"KDD '20"},"container-title":["Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403265","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394486.3403265","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394486.3403265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:47Z","timestamp":1750197707000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":31,"alternative-id":["10.1145\/3394486.3403265","10.1145\/3394486"],"URL":"https:\/\/doi.org\/10.1145\/3394486.3403265","relation":{},"subject":[],"published":{"date-parts":[[2020,8,20]]},"assertion":[{"value":"2020-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}