{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:55:14Z","timestamp":1773377714952,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/isit.2019.8849614","type":"proceedings-article","created":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T21:46:12Z","timestamp":1569534372000},"page":"2299-2303","source":"Crossref","is-referenced-by-count":12,"title":["Harmless interpolation of noisy data in regression"],"prefix":"10.1109","author":[{"given":"Vidya","family":"Muthukumar","sequence":"first","affiliation":[{"name":"BLISS & ML4Wireless, EECS, UC Berkeley"}]},{"given":"Kailas","family":"Vodrahalli","sequence":"additional","affiliation":[{"name":"BLISS & ML4Wireless, EECS, UC Berkeley"}]},{"given":"Anant","family":"Sahai","sequence":"additional","affiliation":[{"name":"BLISS & ML4Wireless, EECS, UC Berkeley"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2822","article-title":"The implicit bias of gradient descent on separable data","volume":"19","author":"soudry","year":"2018","journal-title":"The Journal of Machine Learning Research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1337"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2146090"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOS620"},{"key":"ref35","article-title":"Just interpolate: Kernel","author":"liang","year":"2018","journal-title":"ridgeless\" regression can generalize \" arXiv preprint arXiv 1808 00387"},{"key":"ref34","article-title":"On the margin theory of feedforward neural networks","author":"wei","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1201\/9781420035933"},{"key":"ref11","first-page":"9","article-title":"Random design analysis of ridge regression","author":"hsu","year":"2012","journal-title":"Conference on Learning Theory"},{"key":"ref12","first-page":"40","article-title":"Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition","author":"pati","year":"1993","journal-title":"Signals Systems and Computers 1993 1993 Conference Record of The Twenty-Seventh Asilomar Conference on"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2173241"},{"key":"ref14","article-title":"On tight bounds for the lasso","author":"van de geer","year":"2018"},{"key":"ref15","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","author":"wilson","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"2241","article-title":"Restricted eigenvalue properties for correlated gaussian designs","volume":"11","author":"raskutti","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2007.909108"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2032726"},{"key":"ref19","first-page":"1177","article-title":"Random features for large-scale kernel machines","author":"rahimi","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2059891"},{"key":"ref4","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2032816"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1214\/009053605000000282"},{"key":"ref6","article-title":"Reconciling modern machine learning and the bias-variance trade-off","author":"belkin","year":"2018"},{"key":"ref29","article-title":"The jamming transition as a paradigm to understand the loss landscape of deep neural networks","author":"geiger","year":"2018"},{"key":"ref5","article-title":"Does data interpolation contradict statistical optimality?","author":"belkin","year":"2018"},{"key":"ref8","first-page":"2","article-title":"Algorithmic regularization in overparameterized matrix sensing and neural networks with quadratic activations","author":"li","year":"2018","journal-title":"Conference on Learning Theory"},{"key":"ref7","article-title":"Theoretical insights into the optimization landscape of over-parameterized shallow neural networks","author":"soltanolkotabi","year":"2018","journal-title":"IEEE Transactions on Information Theory"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"key":"ref9","article-title":"Learning and generalization in overparameterized neural networks, going beyond two layers","author":"allen-zhu","year":"2018"},{"key":"ref1","volume":"1","author":"friedman","year":"0","journal-title":"The Elements of Statistical Learning"},{"key":"ref20","article-title":"Introduction to the non-asymptotic analysis of random matrices","author":"vershynin","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0885-064X(91)90002-F"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/0609045"},{"key":"ref24","article-title":"Minimum norm solutions do not always generalize well for over-parameterized problems","author":"shah","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aim.2008.01.010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/S003614450037906X"},{"key":"ref25","author":"bartlett","year":"0","journal-title":"EECS Technical Report"}],"event":{"name":"2019 IEEE International Symposium on Information Theory (ISIT)","location":"Paris, France","start":{"date-parts":[[2019,7,7]]},"end":{"date-parts":[[2019,7,12]]}},"container-title":["2019 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8827389\/8849208\/08849614.pdf?arnumber=8849614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:34:57Z","timestamp":1773347697000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8849614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/isit.2019.8849614","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}