CONF
Orabona_ICML_2011/IDIAP
Ultra-Fast Optimization Algorithm for Sparse Multi Kernel Learning
Orabona, Francesco
Luo, Jie
EXTERNAL
https://publications.idiap.ch/attachments/papers/2011/Orabona_ICML_2011.pdf
PUBLIC
https://publications.idiap.ch/index.php/publications/showcite/Orabona_Idiap-RR-11-2011
Related documents
Proceedings of the 28th International Conference on Machine Learning
2011
Many state-of-the-art approaches for Multi Kernel Learning (MKL) struggle at finding a compromise between performance, sparsity of the solution and speed of the optimization process. In this paper we look at the MKL problem at the same time from a learning and optimization point of view. So, instead of designing a regularizer and then struggling to find an efficient method to minimize it, we design the regularizer while keeping the optimization algorithm in mind. Hence, we introduce a novel MKL formulation, which mixes elements of p-norm and elastic-net kind of regularization. We also propose a fast stochastic gradient descent method that solves the novel MKL formulation. We show theoretically and empirically that our method has 1) state-of-the-art performance on many classification tasks; 2) ex- act sparse solutions with a tunable level of sparsity; 3) a convergence rate bound that depends only logarithmically on the num- ber of kernels used, and is independent of the sparsity required; 4) independence on the particular convex loss function used.
REPORT
Orabona_Idiap-RR-11-2011/IDIAP
Ultra-Fast Optimization Algorithm for Sparse Multi Kernel Learning
Orabona, Francesco
Luo, Jie
EXTERNAL
https://publications.idiap.ch/attachments/reports/2011/Orabona_Idiap-RR-11-2011.pdf
PUBLIC
Idiap-RR-11-2011
2011
Idiap
May 2011
Many state-of-the-art approaches for Multi Kernel Learning (MKL) struggle at finding a compromise between performance, sparsity of the solution and speed of the optimization process. In this paper we look at the MKL problem at the same time from a learning and optimization point of view. So, instead of designing a regularizer and then struggling to find an efficient method to minimize it, we design the regularizer while keeping the optimization algorithm in mind. Hence, we introduce a novel MKL formulation, which mixes elements of p-norm and elastic-net kind of regularization. We also propose a fast stochastic gradient descent method that solves the novel MKL formulation. We show theoretically and empirically that our method has 1) state-of-the-art performance on many classification tasks; 2) ex- act sparse solutions with a tunable level of sparsity; 3) a convergence rate bound that depends only logarithmically on the num- ber of kernels used, and is independent of the sparsity required; 4) independence on the particular convex loss function used.