{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:40:11Z","timestamp":1773376811708,"version":"3.50.1"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2133484,2112665,2217058"],"award-info":[{"award-number":["2133484,2112665,2217058"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,7]]},"DOI":"10.1109\/isit57864.2024.10619481","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:25:01Z","timestamp":1724073901000},"page":"3642-3647","source":"Crossref","is-referenced-by-count":0,"title":["DIST-CURE: A Robust Distributed Learning Algorithm with Cubic Regularized Newton"],"prefix":"10.1109","author":[{"given":"Avishek","family":"Ghosh","sequence":"first","affiliation":[{"name":"IIT,Bombay"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raj Kumar","family":"Maity","sequence":"additional","affiliation":[{"name":"UMass,Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arya","family":"Mazumdar","sequence":"additional","affiliation":[{"name":"UC,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0706-8"},{"key":"ref2","author":"Kone\u010dny","year":"2016","journal-title":"Federated optimization: Distributed machine learning for on-device intelligence"},{"key":"ref3","first-page":"1273","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","author":"McMahan","year":"2017","journal-title":"20th AISTATS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref5","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"35th ICML","author":"Yin","year":"2018"},{"key":"ref6","author":"Blanchard","year":"2017","journal-title":"Byzantine-tolerant machine learning"},{"key":"ref7","first-page":"4613","article-title":"Byzantine stochastic gradient descent","volume":"31","author":"Alistarh","year":"2018","journal-title":"NeurIPS"},{"key":"ref8","author":"Feng","year":"2014","journal-title":"Distributed robust learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref10","author":"Soudry","year":"2016","journal-title":"No bad local minima: Data independent training error guarantees for multilayer neural networks"},{"key":"ref11","first-page":"1233","article-title":"No spurious local minima in nonconvex low rank problems: A unified geometric analysis","volume-title":"34th ICML","volume":"70","author":"Ge","year":"2017"},{"key":"ref12","first-page":"586","article-title":"Deep learning without poor local minima","volume-title":"NeurIPS","volume":"29","author":"Kenji","year":"2016"},{"key":"ref13","author":"Jain","year":"2017","journal-title":"Global convergence of non-convex gradient descent for computing matrix squareroot"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541725"},{"key":"ref15","first-page":"2933","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","volume":"27","author":"Dauphin","year":"2014","journal-title":"NeurIPS"},{"key":"ref16","author":"Bhojanapalli","year":"2016","journal-title":"Global optimality of local search for low rank matrix recovery"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2632162"},{"key":"ref18","author":"Choromanska","year":"2015","journal-title":"The loss surfaces of multilayer networks"},{"key":"ref19","article-title":"Defending against saddle point attack in byzantine-robust distributed learning","volume-title":"ICML","author":"Yin","year":"2019"},{"key":"ref20","first-page":"1724","article-title":"How to escape saddle points efficiently","volume-title":"ICML","author":"Jin","year":"2017"},{"key":"ref21","author":"Xu","year":"2017","journal-title":"First-order stochastic algorithms for escaping from saddle points in almost linear time"},{"key":"ref22","author":"Allen-Zhu","year":"2017","journal-title":"Neon2: Finding local minima via first-order oracles"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3105076"},{"key":"ref24","article-title":"Distributed newton can communicate less and resist byzantine workers","volume-title":"NeurIPS","author":"Ghosh","year":"2020"},{"key":"ref25","first-page":"2731","article-title":"Stochastic variance-reduced cubic regularization for nonconvex optimization","volume-title":"The 22nd AISTATS","author":"Wang","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref27","first-page":"3252","article-title":"Error feedback fixes signsgd and other gradient compression schemes","volume-title":"ICML","author":"Karimireddy","year":"2019"},{"key":"ref28","author":"Lee","year":"2016","journal-title":"Gradient descent converges to minimizers"},{"key":"ref29","author":"Lee","year":"2017","journal-title":"First-order methods almost always avoid saddle points"},{"key":"ref30","author":"Du","year":"2017","journal-title":"Gradient descent can take exponential time to escape saddle points"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-009-0286-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-009-0337-y"},{"key":"ref33","first-page":"2899","article-title":"Stochastic cubic regularization for fast nonconvex optimization","author":"Tripuraneni","year":"2018","journal-title":"NeurIPS"},{"key":"ref34","first-page":"1895","article-title":"Sub-sampled cubic regularization for non-convex optimization","volume-title":"ICML","author":"Kohler","year":"2017"},{"key":"ref35","first-page":"313","article-title":"Cubic regularization with momentum for nonconvex optimization","volume-title":"Uncertainty in Artificial Intelligence","author":"Wang","year":"2020"},{"key":"ref36","first-page":"5990","article-title":"Stochastic variance-reduced cubic regularized newton methods","volume-title":"ICML","author":"Zhou","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/17m1113898"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3055399.3055464"},{"key":"ref39","article-title":"Escape saddle points by a simple gradient-descent based algorithm","author":"Zhang","year":"2021","journal-title":"NeurIPS"},{"key":"ref40","article-title":"Escaping saddle points with compressed sgd","author":"Avdiukhin","year":"2021","journal-title":"NeurIPS"},{"key":"ref41","first-page":"2197","article-title":"vqsgd: Vector quantized stochastic gradient descent","volume-title":"AISTATS","author":"Gandikota","year":"2021"},{"key":"ref42","first-page":"5973","article-title":"The convergence of sparsified gradient methods","author":"Alistarh","year":"2018","journal-title":"NeurIPS"},{"key":"ref43","first-page":"9850","article-title":"Atomo: Communication-efficient learning via atomic sparsification","author":"Wang","year":"2018","journal-title":"NeurIPS"},{"key":"ref44","first-page":"1709","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","author":"Alistarh","year":"2017","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174216"},{"key":"ref46","author":"Bernstein","year":"2018","journal-title":"signsgd with majority vote is communication efficient and byzantine fault tolerant"},{"key":"ref47","author":"Zhao","year":"2018","journal-title":"Federated learning with non-iid data"},{"key":"ref48","volume":"3","author":"Sahu","year":"2018","journal-title":"On the convergence of federated optimization in heterogeneous networks"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref51","first-page":"4615","article-title":"Agnostic federated learning","volume-title":"ICML","author":"Mohri","year":"2019"},{"key":"ref52","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"ICML","author":"Karimireddy","year":"2020"},{"key":"ref53","author":"Fallah","year":"2020","journal-title":"Personalized federated learning: A meta-learning approach"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3418526"},{"key":"ref55","article-title":"Faster non-convex federated learning via global and local momentum","author":"Das","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE International Symposium on Information Theory (ISIT)","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619013\/10619074\/10619481.pdf?arnumber=10619481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:28:29Z","timestamp":1773347309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/isit57864.2024.10619481","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}