Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio. Jastrzk ebski, S., Kenton, Z., Arpit, D., Ballas, N., Fischer, A., Bengio, Y., & Storkey, A. J. In Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III, volume 11141, of Lecture Notes in Computer Science, pages 392–402, 2018. Springer.
Paper doi bibtex @inproceedings{DBLP:conf/icann/JastrzebskiKABF18,
title = {Width of Minima Reached by Stochastic Gradient Descent is Influenced
by Learning Rate to Batch Size Ratio},
author = {Stanis{ł}aw Jastrz{k e}bski and
Zachary Kenton and
Devansh Arpit and
Nicolas Ballas and
Asja Fischer and
Yoshua Bengio and
Amos J. Storkey},
url = {https://doi.org/10.1007/978-3-030-01424-7_39},
doi = {10.1007/978-3-030-01424-7_39},
year = {2018},
date = {2018-01-01},
booktitle = {Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th
International Conference on Artificial Neural Networks, Rhodes, Greece,
October 4-7, 2018, Proceedings, Part III},
volume = {11141},
pages = {392--402},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {76-8485, sda-pub},
pubstate = {published},
tppubtype = {inproceedings}
}
Downloads: 0
{"_id":"EquzN4FFFa8r8M9Au","bibbaseid":"jastrzkebski-kenton-arpit-ballas-fischer-bengio-storkey-widthofminimareachedbystochasticgradientdescentisinfluencedbylearningratetobatchsizeratio-2018","authorIDs":[],"author_short":["Jastrzk ebski, S.","Kenton, Z.","Arpit, D.","Ballas, N.","Fischer, A.","Bengio, Y.","Storkey, A. J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio","author":[{"firstnames":["Stanisław"],"propositions":[],"lastnames":["Jastrzk ebski"],"suffixes":[]},{"firstnames":["Zachary"],"propositions":[],"lastnames":["Kenton"],"suffixes":[]},{"firstnames":["Devansh"],"propositions":[],"lastnames":["Arpit"],"suffixes":[]},{"firstnames":["Nicolas"],"propositions":[],"lastnames":["Ballas"],"suffixes":[]},{"firstnames":["Asja"],"propositions":[],"lastnames":["Fischer"],"suffixes":[]},{"firstnames":["Yoshua"],"propositions":[],"lastnames":["Bengio"],"suffixes":[]},{"firstnames":["Amos","J."],"propositions":[],"lastnames":["Storkey"],"suffixes":[]}],"url":"https://doi.org/10.1007/978-3-030-01424-7_39","doi":"10.1007/978-3-030-01424-7_39","year":"2018","date":"2018-01-01","booktitle":"Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III","volume":"11141","pages":"392–402","publisher":"Springer","series":"Lecture Notes in Computer Science","keywords":"76-8485, sda-pub","pubstate":"published","tppubtype":"inproceedings","bibtex":"@inproceedings{DBLP:conf/icann/JastrzebskiKABF18,\r\ntitle = {Width of Minima Reached by Stochastic Gradient Descent is Influenced \r\nby Learning Rate to Batch Size Ratio},\r\nauthor = {Stanis{ł}aw Jastrz{k e}bski and \r\nZachary Kenton and \r\nDevansh Arpit and \r\nNicolas Ballas and \r\nAsja Fischer and \r\nYoshua Bengio and \r\nAmos J. Storkey},\r\nurl = {https://doi.org/10.1007/978-3-030-01424-7_39},\r\ndoi = {10.1007/978-3-030-01424-7_39},\r\nyear = {2018},\r\ndate = {2018-01-01},\r\nbooktitle = {Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th \r\nInternational Conference on Artificial Neural Networks, Rhodes, Greece, \r\nOctober 4-7, 2018, Proceedings, Part III},\r\nvolume = {11141},\r\npages = {392--402},\r\npublisher = {Springer},\r\nseries = {Lecture Notes in Computer Science},\r\nkeywords = {76-8485, sda-pub},\r\npubstate = {published},\r\ntppubtype = {inproceedings}\r\n}\r\n","author_short":["Jastrzk ebski, S.","Kenton, Z.","Arpit, D.","Ballas, N.","Fischer, A.","Bengio, Y.","Storkey, A. J."],"key":"DBLP:conf/icann/JastrzebskiKABF18","id":"DBLP:conf/icann/JastrzebskiKABF18","bibbaseid":"jastrzkebski-kenton-arpit-ballas-fischer-bengio-storkey-widthofminimareachedbystochasticgradientdescentisinfluencedbylearningratetobatchsizeratio-2018","role":"author","urls":{"Paper":"https://doi.org/10.1007/978-3-030-01424-7_39"},"keyword":["76-8485","sda-pub"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/SmartDataAnalytics/SDA-Publications/master/sda.bib","creationDate":"2020-12-07T16:24:40.673Z","downloads":0,"keywords":["76-8485","sda-pub"],"search_terms":["width","minima","reached","stochastic","gradient","descent","influenced","learning","rate","batch","size","ratio","jastrzk ebski","kenton","arpit","ballas","fischer","bengio","storkey"],"title":"Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio","year":2018,"dataSources":["Smh7N7pGmghKvpo5R","utoK22vdACuMZhGfE"]}