| dc.contributor.author | Golowich, Noah | |
| dc.contributor.author | Rakhlin, Alexander | |
| dc.contributor.author | Shamir, Ohad | |
| dc.date.accessioned | 2021-12-03T15:57:49Z | |
| dc.date.available | 2021-12-03T15:57:49Z | |
| dc.date.issued | 2020 | |
| dc.identifier.uri | https://hdl.handle.net/1721.1/138309 | |
| dc.description.abstract | We study the sample complexity of learning neural networks by providing new bounds on their Rademacher complexity, assuming norm constraints on the parameter matrix of each layer. Compared to previous work, these complexity bounds have improved dependence on the network depth and, under some additional assumptions, are fully independent of the network size (both depth and width). These results are derived using some novel techniques, which may be of independent interest. | en_US |
| dc.language.iso | en | |
| dc.publisher | Oxford University Press (OUP) | en_US |
| dc.relation.isversionof | 10.1093/IMAIAI/IAZ007 | en_US |
| dc.rights | Creative Commons Attribution-Noncommercial-Share Alike | en_US |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | en_US |
| dc.source | arXiv | en_US |
| dc.title | Size-independent sample complexity of neural networks | en_US |
| dc.type | Article | en_US |
| dc.identifier.citation | Golowich, Noah, Rakhlin, Alexander and Shamir, Ohad. 2020. "Size-independent sample complexity of neural networks." Information and Inference, 9 (2). | |
| dc.contributor.department | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences | |
| dc.contributor.department | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems | |
| dc.contributor.department | Massachusetts Institute of Technology. Institute for Data, Systems, and Society | |
| dc.contributor.department | Statistics and Data Science Center (Massachusetts Institute of Technology) | |
| dc.relation.journal | Information and Inference | en_US |
| dc.eprint.version | Author's final manuscript | en_US |
| dc.type.uri | http://purl.org/eprint/type/JournalArticle | en_US |
| eprint.status | http://purl.org/eprint/status/PeerReviewed | en_US |
| dc.date.updated | 2021-12-03T15:54:14Z | |
| dspace.orderedauthors | Golowich, N; Rakhlin, A; Shamir, O | en_US |
| dspace.date.submission | 2021-12-03T15:54:16Z | |
| mit.journal.volume | 9 | en_US |
| mit.journal.issue | 2 | en_US |
| mit.license | OPEN_ACCESS_POLICY | |
| mit.metadata.status | Authority Work and Publication Information Needed | en_US |
