{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T20:00:51Z","timestamp":1766088051058,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"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":[],"published-print":{"date-parts":[[2022,9,23]]},"DOI":"10.1145\/3573942.3573954","type":"proceedings-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T23:45:42Z","timestamp":1684280742000},"page":"78-82","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Effective Training-Time Stacking for Ensembling of Deep Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6055-1854","authenticated-orcid":false,"given":"Polina","family":"Proskura","sequence":"first","affiliation":[{"name":"Skoltech, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1653-0204","authenticated-orcid":false,"given":"Alexey","family":"Zaytsev","sequence":"additional","affiliation":[{"name":"Laboratory of applied research for structured data statistics, Skoltech, Russia"}]}],"member":"320","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"1141","article-title":"On the computational efficiency of training neural networks","volume":"1410","author":"Livni R.","year":"2014","unstructured":"R. Livni, S. Shalev-Shwartz, and O. Shamir, \u201cOn the computational efficiency of training neural networks,\u201d CoRR, vol. abs\/1410.1141, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_2_1","first-page":"00527","article-title":"Computational performance predictions for deep neural network training: A runtime-based approach","volume":"2102","author":"Yu G. X.","year":"2021","unstructured":"G. X. Yu, Y. Gao, P. Golikov, and G. Pekhimenko, \u201cComputational performance predictions for deep neural network training: A runtime-based approach,\u201d CoRR, vol. abs\/2102.00527, 2021.","journal-title":"CoRR"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"e_1_3_2_1_4_1","volume-title":"Snapshot ensembles: Train 1, get m for free","author":"Huang G.","year":"2017","unstructured":"G. Huang, Y. Li, G. Pleiss, Z. Liu, J. E. Hopcroft, and K. Q. Weinberger, \u201cSnapshot ensembles: Train 1, get m for free,\u201d 2017."},{"key":"e_1_3_2_1_5_1","volume-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","author":"Garipov T.","year":"2018","unstructured":"T. Garipov, P. Izmailov, D. Podoprikhin, D. Vetrov, and A. G. Wilson, \u201cLoss surfaces, mode connectivity, and fast ensembling of dnns,\u201d 2018."},{"key":"e_1_3_2_1_6_1","volume-title":"Deep ensembles on a fixed memory budget: One wide network or several thinner ones?","author":"Chirkova N.","year":"2005","unstructured":"N. Chirkova, E. Lobacheva, and D. Vetrov, \u201cDeep ensembles on a fixed memory budget: One wide network or several thinner ones?,\u201d arXiv preprint arXiv:2005.07292, 2020."},{"key":"e_1_3_2_1_7_1","first-page":"282","volume-title":"Proceedings of 3rd international conference on document analysis and recognition","volume":"1","author":"Ho T. K.","year":"1995","unstructured":"T. K. Ho, \u201cRandom decision forests,\u201d in Proceedings of 3rd international conference on document analysis and recognition, vol. 1, pp. 278\u2013282, IEEE, 1995."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_3_2_1_10_1","first-page":"518","volume-title":"Advances in neural information processing systems","author":"Mason L.","year":"2000","unstructured":"L. Mason, J. Baxter, P. L. Bartlett, and M. R. Frean, \u201cBoosting algorithms as gradient descent,\u201d in Advances in neural information processing systems, pp. 512\u2013518, 2000."},{"key":"e_1_3_2_1_11_1","article-title":"A short introduction to boosting","volume":"14","author":"Freund Y.","year":"1999","unstructured":"Y. Freund and R. Schapire, \u201cA short introduction to boosting,\u201d Journal of Japanese Society for Artificial Intelligence, vol. 14, 1999.","journal-title":"Journal of Japanese Society for Artificial Intelligence"},{"key":"e_1_3_2_1_12_1","volume-title":"The return of adaboost. mh: multi-class hamming trees","author":"K\u00e9gl B.","year":"2013","unstructured":"B. K\u00e9gl, \u201cThe return of adaboost. mh: multi-class hamming trees,\u201d arXiv preprint arXiv:1312.6086, 2013."},{"volume-title":"On the mean accuracy of statistical pattern recognizers","author":"Hughes G.","key":"e_1_3_2_1_13_1","unstructured":"G. Hughes, \u201cOn the mean accuracy of statistical pattern recognizers,\u201d IEEE transactions on information theory, vol. 14, no. 1, pp. 55\u201363, 1968."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000015881.36452.6e"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0205872"},{"key":"e_1_3_2_1_16_1","first-page":"02395","article-title":"Ensemble deep learning: A review","volume":"2104","author":"Ganaie M. A.","year":"2021","unstructured":"M. A. Ganaie, M. Hu, M. Tanveer, and P. N. Suganthan, \u201cEnsemble deep learning: A review,\u201d CoRR, vol. abs\/2104.02395, 2021.","journal-title":"CoRR"},{"key":"e_1_3_2_1_17_1","first-page":"02395","article-title":"Ensemble deep learning: A review","volume":"2104","author":"Ganaie M. A.","year":"2021","unstructured":"M. A. Ganaie, M. Hu, M. Tanveer, and P. N. Suganthan, \u201cEnsemble deep learning: A review,\u201d CoRR, vol. abs\/2104.02395, 2021.","journal-title":"CoRR"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.09.182"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"e_1_3_2_1_20_1","volume-title":"On power laws in deep ensembles","author":"Lobacheva E.","year":"2020","unstructured":"E. Lobacheva, N. Chirkova, M. Kodryan, and D. Vetrov, \u201cOn power laws in deep ensembles,\u201d 2020."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8517060"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CITS49457.2020.9232482"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_25_1","volume-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov P.","year":"1803","unstructured":"P. Izmailov, D. Podoprikhin, T. Garipov, D. Vetrov, and A. G. Wilson, \u201cAveraging weights leads to wider optima and better generalization,\u201d arXiv preprint arXiv:1803.05407, 2018."},{"key":"e_1_3_2_1_26_1","volume-title":"Deep residual learning for image recognition","author":"He K.","year":"2015","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d 2015."},{"key":"e_1_3_2_1_27_1","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky, \u201cLearning multiple layers of features from tiny images,\u201d University of Toronto, 05 2012."},{"key":"e_1_3_2_1_28_1","first-page":"07747","article-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","volume":"1708","author":"Xiao H.","year":"2017","unstructured":"H. Xiao, K. Rasul, and R. Vollgraf, \u201cFashion-mnist: a novel image dataset for benchmarking machine learning algorithms,\u201d CoRR, vol. abs\/1708.07747, 2017.","journal-title":"CoRR"}],"event":{"name":"AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","acronym":"AIPR 2022","location":"Xiamen China"},"container-title":["Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3573954","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573942.3573954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:22Z","timestamp":1750182562000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3573954"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":28,"alternative-id":["10.1145\/3573942.3573954","10.1145\/3573942"],"URL":"https:\/\/doi.org\/10.1145\/3573942.3573954","relation":{},"subject":[],"published":{"date-parts":[[2022,9,23]]},"assertion":[{"value":"2023-05-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}