{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T22:20:13Z","timestamp":1772835613543,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"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":[[2021,10,31]]},"DOI":"10.1109\/ieeeconf53345.2021.9723137","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T20:26:46Z","timestamp":1646425606000},"page":"600-607","source":"Crossref","is-referenced-by-count":9,"title":["Depth induces scale-averaging in overparameterized linear Bayesian neural networks"],"prefix":"10.1109","author":[{"given":"Jacob A.","family":"Zavatone-Veth","sequence":"first","affiliation":[{"name":"Harvard University,Department of Physics,Cambridge,MA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cengiz","family":"Pehlevan","sequence":"additional","affiliation":[{"name":"Harvard University,John A. Paulson School of Engineering and Applied Sciences,Cambridge,MA,United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Deep kernel machines and fast solvers for deep kernel machines","author":"aitchison","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02060.x"},{"key":"ref30","article-title":"Random neural networks in the infinite width limit as Gaussian processes","author":"hanin","year":"2021"},{"key":"ref37","article-title":"Scale mixtures of neural network Gaussian processes","author":"lee","year":"2021"},{"key":"ref36","article-title":"Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising","author":"maillard","year":"2021"},{"key":"ref35","article-title":"Statistical limits of dictionary learning: random matrix theory and the spectral replica method","author":"barbier","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2616132"},{"key":"ref10","article-title":"Asymptotics of representation learning in finite Bayesian neural networks","volume":"34","author":"zavatone-veth","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"The principles of deep learning theory","author":"roberts","year":"2021"},{"key":"ref12","first-page":"67","article-title":"Effect of batch learning in multilayer neural networks","author":"fukumizu","year":"1998","journal-title":"Proc of International Conference on Neural Information Processing"},{"key":"ref13","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"saxe","year":"2013"},{"key":"ref14","article-title":"A unifying view on implicit bias in training linear neural networks","author":"yun","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref15","article-title":"Neural networks as kernel learners: The silent alignment effect","author":"atanasov","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.11.031059"},{"key":"ref17","article-title":"The limitations of large width in neural networks: A deep Gaussian process perspective","volume":"34","author":"pleiss","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"130","article-title":"Deep kernel processes","volume":"139","author":"aitchison","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-0427(02)00874-9"},{"key":"ref4","article-title":"Gaussian process behaviour in wide deep neural networks","author":"matthews","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_41"},{"key":"ref3","article-title":"Deep neural networks as Gaussian processes","author":"lee","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref6","article-title":"Exact posterior distributions of wide Bayesian neural networks","author":"hron","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2307\/1969810"},{"key":"ref5","article-title":"Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation","author":"yang","year":"2019"},{"key":"ref8","first-page":"156","article-title":"Why bigger is not always better: on finite and infinite neural networks","volume":"119","author":"aitchison","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref7","first-page":"15156","article-title":"Finite versus infinite neural networks: an empirical study","volume":"33","author":"lee","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"295","article-title":"Computing with infinite networks","author":"williams","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Exact marginal prior distributions of finite Bayesian neural networks","volume":"34","author":"zavatone-veth","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0_2"},{"key":"ref20","volume":"47","author":"vershynin","year":"2018","journal-title":"High-Dimensional Probability An Introduction with Applications in Data Science"},{"key":"ref22","volume":"2","author":"williams","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1002\/9781119541219","author":"magnus","year":"2019","journal-title":"Matrix Differential Calculus with Applications in Statistics and Econometrics"},{"key":"ref24","article-title":"NIST Digital Library of Mathematical Functions","author":"olver","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9469.00089"},{"key":"ref25","first-page":"4697","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","volume":"33","author":"wilson","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2021,10,31]]},"end":{"date-parts":[[2021,11,3]]}},"container-title":["2021 55th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9723034\/9723086\/09723137.pdf?arnumber=9723137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T20:16:49Z","timestamp":1655324209000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf53345.2021.9723137","relation":{},"subject":[],"published":{"date-parts":[[2021,10,31]]}}}