More efficiency in multiple kernel learning

By Alain Rakotomamonjy, Francis R. Bach, Stéphane Canu, Yves Grandvalet. International Conference on Machine Learning, 2007

326 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dccce5d05645a55d9b5b291c02f80e1017892a9e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Optimization for machine learning (2010, methodology): “(28) Note, that computing D(β) and its subgradient D′(β) requires solving the convex quadratic program (24) which is equivalent to the standard SVM dual computed on the composite kernel (19) with a fixed weighting β (Rakotomamonjy et al., 2007).”
Exploring Large Feature Spaces with Hierarchical Multiple Kernel Learning (2008, methodology): “Following [ 9 , 10], we can simply derive an equivalent formulation of Eq. (1).”
Insights from Classifying Visual Concepts with Multiple Kernel Learning (2011, methodology): “simplex [16,17,35,36], we employ a generalized ‘p-norm constraint EbEpƒ1 for p§1 as used in [22,23].”
Consistency of the group Lasso and multiple kernel learning (2007, unknown): “Moreover we denote by 1 q the vector in R q with constant components equal to one, and by I q the identity matrix of size q .”
Learning Multiple Views with Orthogonal Denoising Autoencoders (2016, background): “Multiple Kernel Learning always comes with diverse linear or nonlinear constraints, which makes the objective function complex [13–15].”
A multiple-kernel support vector regression approach for stock market price forecasting (2011, methodology): “Other multiple-kernel learning algorithms include Bach et al. (2004), Sonnenburg et al. (2006), Rakotomamonjy et al. (2007), Rakotomamonjy, Bach, Canu, and Grandvalet (2008), Szafranski et al. (2008) and Gönen et al. (2008).”
Efficient and Accurate Lp-Norm Multiple Kernel Learning (2009, methodology): “While the former can simply be carried out by a support vector machine for a fixed mixture , the latter has been optimized forp = 1 by reduced gradients [ 18 ].”
Discriminative Semi-Supervised Feature Selection Via Manifold Regularization (2009, methodology): “Efficient methods to solve this step include the cutting plane method [49], the subgradient descent method [40], and the level method [56].”
On feature combination for multiclass object classification (2009, methodology): “We compare two different algorithms solving this problem for their runtime performance, namely SILP [18] 2 and SimpleMKL [17] 3 .”
Learning The Discriminative Power-Invariance Trade-Off (2007, methodology): “There are many ways of converting distances to inner products and one is free to choose whichever embedding is most suitable.”
A Binary Classification Framework for Two-Stage Multiple Kernel Learning (2012, methodology): “This one-stage approach was first proposed by (Lanckriet et al., 2004) and has since received significant attention (Rakotomamonjy et al., 2007; Sonnenburg et al., 2006; Cortes et al., 2010a; Kloft et al., 2011; Bach, 2008; Zien & Ong, 2007; Cortes et al., 2009; Sindhwani & Lozano, 2011).”
How far can you get with a modern face recognition test set using only simple features? (2009, methodology): “A full discussion of MKL methods is outside of the scope of the present paper, and is well covered elsewhere [1, 18, 13].”
Multi-View Intact Space Learning (2015, methodology): “[25, 26] proposed simple MKL by exploring an adaptive 2-norm regularization formulation.”
A Survey on Multi-view Learning (2013, methodology): “This novel multiple kernel learning framework is called simple MKL, which has been shown to be more efficient than the SILP problem.”
l p -Norm Multiple Kernel Learning (2011, methodology): “An alternative approach has been studied by Rakotomamonjy et al. (2007) and Zien and Ong (2007), again using hinge loss and l1-norm.”
Multiple Kernel Fuzzy Clustering (2012, unknown): “Efficiency issues of multiple kernel learning were later addressed by Sonnenburg et al. using semiinfinite linear programming [30] and by Rakotomamonjy et al. using a two-step alternation optimization scheme [31].”
Generalized Fisher Score for Feature Selection (2011, methodology): “(19), one possible solution is to relax the indicator variable pi to [0, 1] and transform it into a multiple kernel learning problem [16].”
Multiple Kernel Learning Algorithms (2011, unknown): “Rakotomamonjy et al. (2007, 2008) propose a diﬀerent primal problem for MKL and use a projected gradient method to solve this optimization problem.”