File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Learning overparameterized neural networks via stochastic gradient descent on structured data
Title | Learning overparameterized neural networks via stochastic gradient descent on structured data |
---|---|
Authors | |
Issue Date | 2018 |
Citation | Advances in Neural Information Processing Systems, 2018, v. 2018-December, p. 8157-8166 How to Cite? |
Abstract | Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class classification via stochastic gradient descent (SGD) from random initialization. In the overparameterized setting, when the data comes from mixtures of well-separated distributions, we prove that SGD learns a network with a small generalization error, albeit the network has enough capacity to fit arbitrary labels. Furthermore, the analysis provides interesting insights into several aspects of learning neural networks and can be verified based on empirical studies on synthetic data and on the MNIST dataset. |
Persistent Identifier | http://hdl.handle.net/10722/341245 |
ISSN | 2020 SCImago Journal Rankings: 1.399 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, Yuanzhi | - |
dc.contributor.author | Liang, Yingyu | - |
dc.date.accessioned | 2024-03-13T08:41:18Z | - |
dc.date.available | 2024-03-13T08:41:18Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Advances in Neural Information Processing Systems, 2018, v. 2018-December, p. 8157-8166 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/10722/341245 | - |
dc.description.abstract | Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class classification via stochastic gradient descent (SGD) from random initialization. In the overparameterized setting, when the data comes from mixtures of well-separated distributions, we prove that SGD learns a network with a small generalization error, albeit the network has enough capacity to fit arbitrary labels. Furthermore, the analysis provides interesting insights into several aspects of learning neural networks and can be verified based on empirical studies on synthetic data and on the MNIST dataset. | - |
dc.language | eng | - |
dc.relation.ispartof | Advances in Neural Information Processing Systems | - |
dc.title | Learning overparameterized neural networks via stochastic gradient descent on structured data | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-85064818888 | - |
dc.identifier.volume | 2018-December | - |
dc.identifier.spage | 8157 | - |
dc.identifier.epage | 8166 | - |