TY - GEN
T1 - Bayesian efficient multiple kernel learning
AU - Gönen, Mehmet
PY - 2012
Y1 - 2012
N2 - Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on the computational efficiency issue. However, it is still not feasible to combine many kernels using existing Bayesian approaches due to their high time complexity. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation, which allows us to combine hundreds or thousands of kernels very efficiently. We briefly explain how the proposed method can be extended for multiclass learning and semi-supervised learning. Experiments with large numbers of kernels on benchmark data sets show that our inference method is quite fast, requiring less than a minute. On one bioinformatics and three image recognition data sets, our method outperforms previously reported results with better generalization performance.
AB - Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on the computational efficiency issue. However, it is still not feasible to combine many kernels using existing Bayesian approaches due to their high time complexity. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation, which allows us to combine hundreds or thousands of kernels very efficiently. We briefly explain how the proposed method can be extended for multiclass learning and semi-supervised learning. Experiments with large numbers of kernels on benchmark data sets show that our inference method is quite fast, requiring less than a minute. On one bioinformatics and three image recognition data sets, our method outperforms previously reported results with better generalization performance.
UR - http://www.scopus.com/inward/record.url?scp=84867129730&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867129730&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84867129730
SN - 9781450312851
T3 - Proceedings of the 29th International Conference on Machine Learning, ICML 2012
SP - 1
EP - 8
BT - Proceedings of the 29th International Conference on Machine Learning, ICML 2012
T2 - 29th International Conference on Machine Learning, ICML 2012
Y2 - 26 June 2012 through 1 July 2012
ER -