Excess risk bounds for multitask learning with trace norm regularization

Massimiliano Pontil, Andreas Maurer
Proceedings of the 26th Annual Conference on Learning Theory, PMLR 30:55-76, 2013.

Abstract

Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are independent of the dimension of the input space, which may be infinite as in the case of reproducing kernel Hilbert spaces. A byproduct of the proof are bounds on the expected norm of sums of random positive semidefinite matrices with subexponential moments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v30-Pontil13, title = {Excess risk bounds for multitask learning with trace norm regularization}, author = {Pontil, Massimiliano and Maurer, Andreas}, booktitle = {Proceedings of the 26th Annual Conference on Learning Theory}, pages = {55--76}, year = {2013}, editor = {Shalev-Shwartz, Shai and Steinwart, Ingo}, volume = {30}, series = {Proceedings of Machine Learning Research}, address = {Princeton, NJ, USA}, month = {12--14 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v30/Pontil13.pdf}, url = {https://proceedings.mlr.press/v30/Pontil13.html}, abstract = {Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are independent of the dimension of the input space, which may be infinite as in the case of reproducing kernel Hilbert spaces. A byproduct of the proof are bounds on the expected norm of sums of random positive semidefinite matrices with subexponential moments.} }
Endnote
%0 Conference Paper %T Excess risk bounds for multitask learning with trace norm regularization %A Massimiliano Pontil %A Andreas Maurer %B Proceedings of the 26th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2013 %E Shai Shalev-Shwartz %E Ingo Steinwart %F pmlr-v30-Pontil13 %I PMLR %P 55--76 %U https://proceedings.mlr.press/v30/Pontil13.html %V 30 %X Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are independent of the dimension of the input space, which may be infinite as in the case of reproducing kernel Hilbert spaces. A byproduct of the proof are bounds on the expected norm of sums of random positive semidefinite matrices with subexponential moments.
RIS
TY - CPAPER TI - Excess risk bounds for multitask learning with trace norm regularization AU - Massimiliano Pontil AU - Andreas Maurer BT - Proceedings of the 26th Annual Conference on Learning Theory DA - 2013/06/13 ED - Shai Shalev-Shwartz ED - Ingo Steinwart ID - pmlr-v30-Pontil13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 30 SP - 55 EP - 76 L1 - http://proceedings.mlr.press/v30/Pontil13.pdf UR - https://proceedings.mlr.press/v30/Pontil13.html AB - Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are independent of the dimension of the input space, which may be infinite as in the case of reproducing kernel Hilbert spaces. A byproduct of the proof are bounds on the expected norm of sums of random positive semidefinite matrices with subexponential moments. ER -
APA
Pontil, M. & Maurer, A.. (2013). Excess risk bounds for multitask learning with trace norm regularization. Proceedings of the 26th Annual Conference on Learning Theory, in Proceedings of Machine Learning Research 30:55-76 Available from https://proceedings.mlr.press/v30/Pontil13.html.

Related Material