{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T05:17:44Z","timestamp":1740719864525,"version":"3.38.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886208","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"5668-5674","source":"Crossref","is-referenced-by-count":0,"title":["A Stochastic Quasi-Newton Method for Non-convex Optimization with Non-uniform Smoothness"],"prefix":"10.1109","author":[{"given":"Zhenyu","family":"Sun","sequence":"first","affiliation":[{"name":"Northwestern University,Electrical & Computer Engineering,Evanston,USA,IL 60208"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ermin","family":"Wei","sequence":"additional","affiliation":[{"name":"Northwestern University,Electrical & Computer Engineering and Industrial Engineering & Management Science,Evanston,USA,IL 60208"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Natasha 2: Faster non-convex optimization than sgd","volume":"31","author":"Allen-Zhu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"699","article-title":"Variance reduction for faster non-convex optimization","volume-title":"International conference on machine learning","author":"Allen-Zhu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01822-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/140954362"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2957843"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2968826.2969010"},{"key":"ref8","article-title":"Spider: Near-optimal nonconvex optimization via stochastic path-integrated differential estimator","volume":"31","author":"Fang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"International conference on machine learning","author":"Gehring"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0871-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2512329"},{"key":"ref13","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume":"26","author":"Johnson","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1895","article-title":"Sub-sampled cubic regularization for non-convex optimization","volume-title":"International Conference on Machine Learning","author":"Kohler"},{"key":"ref15","article-title":"Non-convex finite-sum optimization via scsg methods","volume":"30","author":"Lei","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","first-page":"6286","article-title":"Page: A simple and optimal probabilistic gradient estimator for nonconvex optimization","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref17","article-title":"Zerosarah: Efficient nonconvex finite-sum optimization with zero full gradient computation","author":"Li","year":"2021","journal-title":"arXiv preprint arXiv:2103.01447"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref19","article-title":"A variance reduced stochastic newton method","author":"Lucchi","year":"2015","journal-title":"arXiv preprint arXiv:1503.08316"},{"key":"ref20","first-page":"7555","article-title":"Leveraging non-uniformity in first-order non-convex optimization","volume-title":"International Conference on Machine Learning","author":"Mei"},{"key":"ref21","article-title":"Regularizing and optimizing 1stm language models","author":"Merity","year":"2017","journal-title":"arxiv 2017. arXiv preprint arXiv:1708.02182"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2357775"},{"key":"ref23","first-page":"249","article-title":"A linearly-convergent stochastic 1-bfgs algorithm","author":"Moritz","year":"2016","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref24","first-page":"2613","article-title":"Sarah: A novel method for machine learning problems using stochastic recursive gradient","volume-title":"International conference on machine learning","author":"Nguyen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/b98874"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"issue":"1","key":"ref27","first-page":"4455","article-title":"Proxsarah: An efficient algorithmic framework for stochastic composite nonconvex optimization","volume":"21","author":"Pham","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref28","first-page":"1504","article-title":"Understanding gradient clipping in incremental gradient methods","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Qian"},{"key":"ref29","first-page":"314","article-title":"Stochastic variance reduction for nonconvex optimization","volume-title":"International conference on machine learning","author":"Reddi"},{"key":"ref30","article-title":"Variance-reduced clipping for non-convex optimization","author":"Reisizadeh","year":"2023","journal-title":"arXiv preprint arXiv:2303.00883"},{"key":"ref31","first-page":"400","article-title":"A stochastic approximation method. The annals of mathematical statistics","author":"Robbins","year":"1951"},{"key":"ref32","first-page":"436","article-title":"A stochastic quasi-newton method for online convex optimization","author":"Schraudolph","year":"2007","journal-title":"Artificial intelligence and statistics"},{"key":"ref33","first-page":"604","article-title":"Fast large-scale optimization by unifying stochastic gradient and quasi-newton methods","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref34","first-page":"3693","article-title":"Convergence of stein variational gradient descent under a weaker smoothness condition","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Sun"},{"key":"ref35","article-title":"A stochastic quasi-newton method for nonconvex optimization with non-uniform smoothness","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv:2403.15244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/15M1053141"},{"key":"ref37","first-page":"611","volume-title":"Convolutional neural networks: an overview and application in radiology. Insights into imaging","volume":"9","author":"Yamashita","year":"2018"},{"key":"ref38","article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","author":"Zhang","year":"2019","journal-title":"arXiv preprint arXiv:1905.11881"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056947"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3023-7"},{"key":"ref41","first-page":"5990","article-title":"Stochastic variance-reduced cubic regularized newton methods","volume-title":"International Conference on Machine Learning","author":"Zhou"},{"issue":"1","key":"ref42","first-page":"4130","article-title":"Stochastic nested variance reduction for nonconvex optimization","volume":"21","author":"Zhou","year":"2020","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","start":{"date-parts":[[2024,12,16]]},"location":"Milan, Italy","end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886208.pdf?arnumber=10886208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:24:40Z","timestamp":1740641080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886208","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}