{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:03:50Z","timestamp":1743098630868,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031777301"},{"type":"electronic","value":"9783031777318"}],"license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-77731-8_33","type":"book-chapter","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:42:26Z","timestamp":1732034546000},"page":"361-374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Loss Function Role in Processing Sequences with Heavy-Tailed Distributions"],"prefix":"10.1007","author":[{"given":"Mikhail","family":"Gritskikh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2938-0575","authenticated-orcid":false,"given":"Artem","family":"Isakov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1361-6037","authenticated-orcid":false,"given":"Natalia","family":"Gusarova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1485-1166","authenticated-orcid":false,"given":"Dmitriy","family":"Dobrenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1886-2867","authenticated-orcid":false,"given":"Ivan","family":"Tomilov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5483-716X","authenticated-orcid":false,"given":"Aleksandra","family":"Vatian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"33_CR1","unstructured":"Gurbuzbalaban M., et al.: Heavy Tails in ML: Structure, Stability, Dynamics. https:\/\/neurips.cc\/virtual\/2023\/workshop\/66530"},{"issue":"1","key":"33_CR2","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3390\/fractalfract8010007","volume":"8","author":"W Song","year":"2024","unstructured":"Song, W., Chen, D., Zio, E.: Heavy tail and long-range dependence for skewed time series prediction based on a fractional Weibull process. Fractal Fract. 8(1), 7 (2024). https:\/\/doi.org\/10.3390\/fractalfract8010007","journal-title":"Fractal Fract."},{"issue":"1","key":"33_CR3","doi-asserted-by":"publisher","first-page":"120588","DOI":"10.1016\/j.eswa.2023.120588","volume":"230","author":"D Szarek","year":"2023","unstructured":"Szarek, D., et al.: Non-Gaussian feature distribution forecasting based on ConvLSTM neural network and its application to robust machine condition prognosis. ACM Digit. Libr. 230(1), 120588 (2023). https:\/\/doi.org\/10.1016\/j.eswa.2023.120588","journal-title":"ACM Digit. Libr."},{"key":"33_CR4","unstructured":"Vaswani, A., et al.: Attention is all you need. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA"},{"key":"33_CR5","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1038\/s41467-020-17591-w","volume":"11","author":"SM Mousavi","year":"2020","unstructured":"Mousavi, S.M., Ellsworth, W.L., Zhu, W., et al.: Earthquake transformer\u2014an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nat. Commun. 11, 3952 (2020)","journal-title":"Nat. Commun."},{"key":"33_CR6","first-page":"448","volume-title":"Medical Statistics: A Textbook for the Health Sciences","author":"D Machin","year":"2021","unstructured":"Machin, D., Campbell, M.J., Walters, S.J.: Medical Statistics: A Textbook for the Health Sciences, 5th edn., p. 448. Wiley-Blackwell (2021)","edition":"5"},{"key":"33_CR7","unstructured":"Geshkovski, B., et al.: A Mathematical Perspective on Transformers (2024). arXiv:2312.10794v3"},{"key":"33_CR8","unstructured":"Vuckovic, J., Baratin, A., Combes, R.T.: A Mathematical Theory of Attention. http:\/\/arxiv.org\/abs\/2007.02876v2"},{"key":"33_CR9","unstructured":"Sanford, C., Hsu, D., Telgarsky, M.: Representational Strengths and Limitations of Transformers (2023). arXiv:2306.02896v2"},{"key":"33_CR10","doi-asserted-by":"publisher","unstructured":"Balim, H., et al.: Can Transformers Learn Optimal Filtering for Unknown Systems? (2024). arXiv:2308.08536v3. https:\/\/doi.org\/10.1080\/15598608.2013.824823","DOI":"10.1080\/15598608.2013.824823"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Liu, B., Coblenz, M., Grothe, O.: Predicting grid frequency short-term dynamics with Gaussian processes and sequence modeling. In: E-Energy \u201824: The 15th ACM International Conference on Future and Sustainable Energy Systems, Singapore, Singapore (2024)","DOI":"10.1145\/3632775.3662160"},{"key":"33_CR12","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.future.2023.02.015","volume":"144","author":"F Zeng","year":"2023","unstructured":"Zeng, F., et al.: Multivariate time series anomaly detection with adversarial transformer architecture in the Internet of Things. Futur. Gener. Comput. Syst. 144, 244\u2013255 (2023)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"33_CR13","unstructured":"Chen, J., Kunstner, F., Schmidt, M.: Heavy-tailed noise does not explain the gap between SGD and Adam on transformers. In: OPT2021: 13th Annual Workshop on Optimization for Machine Learning, pp. 55"},{"key":"33_CR14","doi-asserted-by":"publisher","unstructured":"Du, J., et al.: Handling heavy-tailed input of transformer inference on GPUs. In: ICS \u201822: Proceedings of the 36th ACM International Conference on Supercomputing, no. 38, pp. 1\u201311 (2022). https:\/\/doi.org\/10.1145\/3524059.3532372","DOI":"10.1145\/3524059.3532372"},{"key":"33_CR15","unstructured":"Kunstner, F., et al.: Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models. https:\/\/arxiv.org\/html\/2402.19449v1"},{"key":"33_CR16","unstructured":"Ahn, K., et al.: Linear Attention is (Maybe) All You Need (to Understand Transformer Optimization) (2024). arXiv:2310.01082v2"},{"key":"33_CR17","doi-asserted-by":"publisher","first-page":"1292842","DOI":"10.3389\/fncom.2023.1292842","volume":"17","author":"B Lee","year":"2023","unstructured":"Lee, B., et al.: Burst and memory-aware transformer: capturing temporal heterogeneity. Front. Comput. Neurosci. 17, 1292842 (2023). https:\/\/doi.org\/10.3389\/fncom.2023.1292842","journal-title":"Front. Comput. Neurosci."},{"issue":"8","key":"33_CR18","doi-asserted-by":"publisher","first-page":"e0237462","DOI":"10.1371\/journal.pone.0237462","volume":"15","author":"W Zhao","year":"2020","unstructured":"Zhao, W., et al.: Type-I heavy tailed family with applications in medicine, engineering and insurance. PLoS ONE 15(8), e0237462 (2020). https:\/\/doi.org\/10.1371\/journal.pone.0237462","journal-title":"PLoS ONE"},{"issue":"4","key":"33_CR19","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1080\/15598608.2013.824823","volume":"8","author":"J Gardiner","year":"2014","unstructured":"Gardiner, J., et al.: Fitting heavy-tailed distributions to health care data by parametric and Bayesian methods. J. Stat. Theory Pract. 8(4), 619 (2014)","journal-title":"J. Stat. Theory Pract."},{"key":"33_CR20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0034222","author":"C Burton","year":"2012","unstructured":"Burton, C.: Heavy tailed distributions of effect sizes in systematic reviews of complex interventions. PLoS ONE (2012). https:\/\/doi.org\/10.1371\/journal.pone.0034222","journal-title":"PLoS ONE"},{"key":"33_CR21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0294445","author":"P Liu","year":"2023","unstructured":"Liu, P., Zheng, Y.: Heavy-tailed distributions of confirmed COVID-19 cases and deaths in spatiotemporal space. PLoS ONE (2023). https:\/\/doi.org\/10.1371\/journal.pone.0294445","journal-title":"PLoS ONE"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Karlsson, M., et al.: Getting the right tail right: modeling tails of health expenditure distributions. In: ZEW - Centre for European Economic Research Discussion Paper No. 23\u2013045, pp. 41 (2023)","DOI":"10.3386\/w31444"},{"key":"33_CR23","doi-asserted-by":"publisher","unstructured":"DeWitt, M.E., et al.: The Challenges of Surveying Heavy-tail Distributions for Use in Infectious Disease Dynamics (2023). https:\/\/doi.org\/10.1101\/2023.07.05.23292248v1","DOI":"10.1101\/2023.07.05.23292248v1"},{"key":"33_CR24","unstructured":"Nerella, S.: et al.: Transformers in Healthcare: A Survey. https:\/\/arxiv.org\/pdf\/2307.00067"},{"issue":"1","key":"33_CR25","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10916-024-02043-5","volume":"48","author":"K Denecke","year":"2024","unstructured":"Denecke, K., May, A., Rivera-Romero, O.: Transformer models in healthcare: a survey and thematic analysis of potentials, shortcomings and risks. J. Med. Syst. 48(1), 23 (2024)","journal-title":"J. Med. Syst."},{"key":"33_CR26","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s10462-023-10677-z","volume":"57","author":"CA Siebra","year":"2024","unstructured":"Siebra, C.A., Kurpicz-Briki, M., Wac, K.: Transformers in health: a systematic review on architectures for longitudinal data analysis. Artif. Intell. Rev. 57, 32 (2024). https:\/\/doi.org\/10.1007\/s10462-023-10677-z","journal-title":"Artif. Intell. Rev."},{"key":"33_CR27","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","volume":"4","author":"L Rasmy","year":"2021","unstructured":"Rasmy, L., Xiang, Y., Xie, Z., et al.: Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. npj Digit. Med. 4, 86 (2021). https:\/\/doi.org\/10.1038\/s41746-021-00455-y","journal-title":"npj Digit. Med."},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: Hitanet: hierarchical time-aware attention networks for risk prediction on electronic health records. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 647\u2013656 (2020)","DOI":"10.1145\/3394486.3403107"},{"key":"33_CR29","doi-asserted-by":"publisher","first-page":"7155","DOI":"10.1038\/s41598-020-62922-y","volume":"10","author":"Y Li","year":"2020","unstructured":"Li, Y., Rao, S., Solares, J.R.A., et al.: BEHRT: transformer for electronic health records. Sci. Rep. 10, 7155 (2020). https:\/\/doi.org\/10.1038\/s41598-020-62922-y","journal-title":"Sci. Rep."},{"key":"33_CR30","first-page":"106248","volume":"151","author":"X Pu","year":"2022","unstructured":"Pu, X., et al.: EEGDnet: fusing non-local and local self-similarity for EEG signal denoising with transformer Comput. Biol. Med. Part A 151, 106248 (2022)","journal-title":"Biol. Med. Part A"},{"issue":"1","key":"33_CR31","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1186\/s12911-021-01546-2","volume":"21","author":"C Che","year":"2021","unstructured":"Che, C., et al.: Constrained transformer network for ECG signal processing and arrhythmia classification. BMC Med. Inform. Decis. Mak. 21(1), 184 (2021). https:\/\/doi.org\/10.1186\/s12911-021-01546-2","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"33_CR32","doi-asserted-by":"publisher","first-page":"105362","DOI":"10.1016\/j.compbiomed.2022.105362","volume":"144","author":"X Wu","year":"2022","unstructured":"Wu, X., et al.: Long short-term memory model \u2013 a deep learning approach for medical data with irregularity in cancer predication with tumor markers. Comput. Biol. Med. 144, 105362 (2022)","journal-title":"Comput. Biol. Med."},{"key":"33_CR33","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s12911-020-01345-1","volume":"21","author":"A Guo","year":"2021","unstructured":"Guo, A., Beheshti, R., Khan, Y.M., et al.: Predicting cardiovascular health trajectories in time-series electronic health records with LSTM models. BMC Med. Inform. Decis. Mak. 21, 5 (2021)","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"33_CR34","doi-asserted-by":"publisher","unstructured":"Ren H., et al.: RAPT: pre-training of time-aware transformer for learning robust healthcare representation. In: KDD \u201821: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 3503\u20133511 (2021). https:\/\/doi.org\/10.1145\/3447548.3467069","DOI":"10.1145\/3447548.3467069"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77731-8_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:47:00Z","timestamp":1732034820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77731-8_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"ISBN":["9783031777301","9783031777318"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77731-8_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"14 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valencia","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}