{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:57:55Z","timestamp":1773377875574,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/isit44484.2020.9174363","type":"proceedings-article","created":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T17:28:01Z","timestamp":1598290081000},"page":"2628-2633","source":"Crossref","is-referenced-by-count":4,"title":["On Byzantine-Resilient High-Dimensional Stochastic Gradient Descent"],"prefix":"10.1109","author":[{"given":"Deepesh","family":"Data","sequence":"first","affiliation":[{"name":"University of California,Los Angeles,USA"}]},{"given":"Suhas","family":"Diggavi","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3309697.3331499"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref12","first-page":"119","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","author":"blanchard","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref13","first-page":"902","article-title":"DRACO: byzantine-resilient distributed training via redundant gradients","author":"chen","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref14","first-page":"10320","article-title":"DETOX: A redundancy-based framework for faster and more robust gradient aggregation","author":"rajput","year":"2019","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849857"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849857"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.2876048"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(78)90006-3"},{"key":"ref4","article-title":"Stochastic, distributed and federated optimization for machine learning","author":"konecn\u00fd","year":"0","journal-title":"CoRR"},{"key":"ref27","first-page":"523","article-title":"Mathematics and picturing of data","volume":"6","author":"tukey","year":"1975","journal-title":"Proc ICME"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref5","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"konecn\u00fd","year":"2016","journal-title":"CoRR"},{"key":"ref8","first-page":"7074","article-title":"Defending against saddle point attack in byzantine-robust distributed learning","author":"yin","year":"2019","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref7","first-page":"5636","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","author":"yin","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref9","first-page":"4618","article-title":"Byzantine stochastic gradient descent","author":"alistarh","year":"2018","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2016.76"},{"key":"ref22","first-page":"45:1","article-title":"Resilience: A criterion for learning in the presence of arbitrary outliers","author":"steinhardt","year":"2018","journal-title":"Conference on Innovations in Theoretical Computer science (ITCS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2016.85"},{"key":"ref24","article-title":"Byzantine-resilient SGD in high dimensions on heterogeneous data","author":"data","year":"2020","journal-title":"CoRR"},{"key":"ref23","article-title":"Recent advances in algorithmic high-dimensional robust statistics","author":"diakonikolas","year":"2019","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref25","first-page":"448","article-title":"A survey of sampling from contaminated distributions","volume":"2","author":"tukey","year":"1960","journal-title":"Contributions to Probability and Statistics"}],"event":{"name":"2020 IEEE International Symposium on Information Theory (ISIT)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2020,6,21]]},"end":{"date-parts":[[2020,6,26]]}},"container-title":["2020 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9166581\/9173928\/09174363.pdf?arnumber=9174363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:35:26Z","timestamp":1773347726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9174363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/isit44484.2020.9174363","relation":{},"subject":[],"published":{"date-parts":[[2020,6]]}}}