File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: SDNA: Stochastic Dual Newton Ascent for epirical risk minimization
Title | SDNA: Stochastic Dual Newton Ascent for epirical risk minimization |
---|---|
Authors | |
Issue Date | 2016 |
Publisher | MIT Press. The Journal's web site is located at http://mitpress.mit.edu/jmlr |
Citation | The 33 rd International Conference on Machine Learning (ICML 2016), New York, NY., 19-24 June 2016. In JMLR: Workshop and Conference Proceedings, 2016, v. 48, p. 1-10 How to Cite? |
Abstract | We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subset of the dual variables. However, unlike existing methods such as stochastic dual coordinate ascent, SDNA is capable of utilizing all local curvature information contained in the examples, which leads to striking improvements in both theory and practice – sometimes by orders of magnitude. In the special case when an L2-regularizer is used in the primal, the dual problem is a concave quadratic maximization problem plus a separable term. In this regime, SDNA in each step solves a proximal subproblem involving a random principal submatrix of the Hessian of the quadratic function; whence the name of the method. |
Description | This journal vol. entitled: Proceedings of the 33 rd International Conference on Machine Learning, ICML 2016 The full version of this paper can be found on https://arxiv.org/abs/1502.02268 |
Persistent Identifier | http://hdl.handle.net/10722/235018 |
ISSN | 2023 Impact Factor: 4.3 2023 SCImago Journal Rankings: 2.796 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Qu, Z | - |
dc.contributor.author | Richtarik, P | - |
dc.contributor.author | Takac, M | - |
dc.contributor.author | Fercoq, O | - |
dc.date.accessioned | 2016-10-14T13:50:45Z | - |
dc.date.available | 2016-10-14T13:50:45Z | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | The 33 rd International Conference on Machine Learning (ICML 2016), New York, NY., 19-24 June 2016. In JMLR: Workshop and Conference Proceedings, 2016, v. 48, p. 1-10 | - |
dc.identifier.issn | 1532-4435 | - |
dc.identifier.uri | http://hdl.handle.net/10722/235018 | - |
dc.description | This journal vol. entitled: Proceedings of the 33 rd International Conference on Machine Learning, ICML 2016 | - |
dc.description | The full version of this paper can be found on https://arxiv.org/abs/1502.02268 | - |
dc.description.abstract | We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subset of the dual variables. However, unlike existing methods such as stochastic dual coordinate ascent, SDNA is capable of utilizing all local curvature information contained in the examples, which leads to striking improvements in both theory and practice – sometimes by orders of magnitude. In the special case when an L2-regularizer is used in the primal, the dual problem is a concave quadratic maximization problem plus a separable term. In this regime, SDNA in each step solves a proximal subproblem involving a random principal submatrix of the Hessian of the quadratic function; whence the name of the method. | - |
dc.language | eng | - |
dc.publisher | MIT Press. The Journal's web site is located at http://mitpress.mit.edu/jmlr | - |
dc.relation.ispartof | Journal of Machine Learning Research | - |
dc.rights | Journal of Machine Learning Research. Copyright © MIT Press. | - |
dc.rights | Author holds the copyright | - |
dc.title | SDNA: Stochastic Dual Newton Ascent for epirical risk minimization | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Qu, Z: zhengqu@hku.hk | - |
dc.identifier.authority | Qu, Z=rp02096 | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.hkuros | 269840 | - |
dc.identifier.volume | 48 | - |
dc.identifier.spage | 1 | - |
dc.identifier.epage | 10 | - |
dc.publisher.place | United States | - |
dc.customcontrol.immutable | sml 161017 - embargo till 170601 | - |
dc.identifier.issnl | 1532-4435 | - |