{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:13:56Z","timestamp":1735103636937,"version":"3.32.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800306","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["An Optimizer for Conformer Based on Conjugate Gradient Method"],"prefix":"10.1109","author":[{"given":"Wenyi","family":"Yu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","year":"2015"},{"key":"ref2","article-title":"Deep learning via hessian-free optimization","volume-title":"Proc. ICML","author":"Martens","year":"2010"},{"key":"ref3","article-title":"Scalable second order optimization for deep learning","author":"Anil","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown","year":"2020"},{"volume-title":"PaLM 2 technical report","year":"2023","author":"Anil","key":"ref5"},{"volume-title":"LLaMA: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref6"},{"volume-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","year":"2023","author":"Chiang","key":"ref7"},{"key":"ref8","article-title":"Optimizing neural networks with kronecker-factored approximate curvature","volume-title":"Proc. ICML","author":"Martens","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref10","article-title":"Layer normalization","volume-title":"Proc. NIPS","author":"Ba","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref12","first-page":"273","article-title":"Building a large annotated corpus of en-glish: The penn treebank","author":"Marcinkiewicz","year":"1994","journal-title":"Using Large Corpora"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref14","article-title":"Fast approximate natural gradient descent in a kronecker factored eigenbasis","volume-title":"Proc. NeurIPS, Montreal","author":"George","year":"2018"},{"key":"ref15","article-title":"Shampoo: Preconditioned stochastic tensor optimization","volume-title":"Proc. ICML","author":"Gupta","year":"2018"},{"key":"ref16","article-title":"Limitations of the empirical fisher approximation for natural gradient descent","volume-title":"Proc. NeurIPS","author":"Kunstner","year":"2019"},{"volume-title":"Scalable second order optimization for deep learning","year":"2021","author":"Anil","key":"ref17"},{"key":"ref18","article-title":"Tensor normal training for deep learning models","volume-title":"Proc. NeurIPS","author":"Ren","year":"2021"},{"key":"ref19","article-title":"Krylov subspace descent for deep learning","volume-title":"Proc. AISTATS","author":"Vinyals","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268933"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.05.011"},{"key":"ref22","article-title":"Neural learning in structured parameter spaces-natural riemannian gradient","volume-title":"Proc. NIPS","author":"Amari","year":"1996"},{"issue":"67\u201368","key":"ref23","first-page":"7","article-title":"Numerical optimization","volume":"35","author":"Wright","year":"1999","journal-title":"Springer Science"},{"volume-title":"An introduction to the conjugate gradient method without the agonizing pain","year":"1994","author":"Shewchuk","key":"ref24"},{"key":"ref25","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.1.147"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/08997660260028683"},{"key":"ref28","article-title":"Learning recurrent neural networks with hessian-free optimization","volume-title":"Proc. ICML","author":"Martens","year":"2011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800306.pdf?arnumber=10800306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:19Z","timestamp":1735021579000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800306","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}