{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T15:41:43Z","timestamp":1762443703225,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447855","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"6075-6079","source":"Crossref","is-referenced-by-count":1,"title":["Learning Dynamics of Low-Precision Clipped SGD with Momentum"],"prefix":"10.1109","author":[{"given":"Roula","family":"Nassif","sequence":"first","affiliation":[{"name":"Université Côte d'Azur,I3S Laboratory, CNRS,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soummya","family":"Kar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Vlaski","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5813","article-title":"Training quantized nets: A deeper understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Li"},{"key":"ref2","first-page":"1737","article-title":"Deep learning with limited numerical precision","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Gupta"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080248"},{"key":"ref4","first-page":"5151","article-title":"Scalable methods for 8-bit training of neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Banner"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00204"},{"key":"ref6","first-page":"2656","article-title":"Taming the wild: A unified analysis of HOGWILD-style algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"28","author":"De Sa"},{"article-title":"High-accuracy low-precision training","year":"2018","author":"De Sa","key":"ref7"},{"key":"ref8","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Alistarh"},{"article-title":"Low-precision stochastic gradient Langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Zhang","key":"ref9"},{"key":"ref10","article-title":"Quantization for decentralized learning under subspace constraints","author":"Nassif","year":"2022","journal-title":"Submitted for publication"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref11"},{"article-title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Zhang","key":"ref12"},{"key":"ref13","first-page":"7325","article-title":"Stability and convergence of stochastic gradient clipping: Beyond Lipschitz continuity and smoothness","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Mai"},{"article-title":"Stochastic optimization with heavy-tailed noise via accelerated gradient clipping","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Gorbunov","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503173"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-020-00220-z"},{"key":"ref19","first-page":"9630","article-title":"Understanding the role of momentum in stochastic gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Gitman"},{"key":"ref20","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"97","author":"Yu"},{"article-title":"An improved analysis of stochastic gradient descent with momentum","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Liu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3277211"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747154"},{"key":"ref24","first-page":"3478","article-title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"97","author":"Koloskova"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3176253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/2200000051"},{"volume-title":"Introduction to Optimization","year":"1987","author":"Polyak","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728716"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/0471722146"},{"volume-title":"Principles of Mathematical Analysis","year":"1953","author":"Rudin","key":"ref30"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447855.pdf?arnumber=10447855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:35:32Z","timestamp":1722573332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447855","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}