{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:08Z","timestamp":1774419428098,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889234","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Variance-reduced Clipping for Non-convex Optimization"],"prefix":"10.1109","author":[{"given":"Amirhossein","family":"Reisizadeh","sequence":"first","affiliation":[{"name":"MIT,LIDS,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochuan","family":"Li","sequence":"additional","affiliation":[{"name":"MIT,LIDS,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhro","family":"Das","sequence":"additional","affiliation":[{"name":"IBM Research,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Jadbabaie","sequence":"additional","affiliation":[{"name":"MIT,LIDS,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"Zhang","year":"2019"},{"key":"ref2","article-title":"Provable adaptivity in adam","author":"Wang","year":"2022"},{"key":"ref3","article-title":"Spider: Near-optimal non- convex optimization via stochastic path-integrated differential estimator","volume":"31","author":"Fang","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01822-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889234"},{"key":"ref6","article-title":"Regularizing and optimizing lstm language models","author":"Merity","year":"2017"},{"key":"ref7","first-page":"1243","article-title":"Con- volutional sequence to sequence learning","volume-title":"International conference on machine learning","author":"Gehring"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1202"},{"key":"ref9","first-page":"15 511","article-title":"Improved analysis of clipping algorithms for non-convex optimization","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Informa- tion Processing Systems"},{"key":"ref10","first-page":"1504","article-title":"Understanding gradient clipping in incremental gradient methods","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Qian"},{"key":"ref11","volume-title":"Introductory lectures on convex optimization: A basic course.","volume":"87","author":"Nesterov","year":"2003"},{"key":"ref12","first-page":"699","article-title":"Variance reduction for faster non-convex optimization","volume-title":"International conference on machine learning","author":"Allen-Zhu"},{"key":"ref13","first-page":"314","article-title":"Stochastic vari- ance reduction for nonconvex optimization","volume-title":"International conference on machine learning","author":"Reddi"},{"key":"ref14","article-title":"Non-convex finite-sum opti- mization via scsg methods","volume":"30","author":"Lei","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"On the ineffectiveness of variance reduced optimization for deep learning","volume":"32","author":"Defazio","year":"2019","journal-title":"Advances in Neural Information Pro- cessing Systems"},{"key":"ref16","article-title":"Saga: A fast incremental gradient method with support for non-strongly convex composite ob- jectives","volume":"27","author":"Defazio","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"A stochastic gradient method with an exponential convergence _rate for finite training sets","volume":"25","author":"Roux","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Stochastic dual coordinate as- cent methods for regularized loss minimization","author":"Shalev-Shwartz","year":"2012"},{"key":"ref19","article-title":"Momentum-based variance reduction in non-convex sgd","volume":"32","author":"Cutkosky","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","article-title":"THE MNIST DATABASE of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref22","article-title":"Zerosarah: Efficient nonconvex finite-sum optimization with zero full gradient computation","author":"Li","year":"2021"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889234.pdf?arnumber=10889234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:50Z","timestamp":1774416170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889234","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}