Open AccessPosted Content
The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning
Marius Kloft,Gilles Blanchard +1 more
Reads0
Chats0
TLDR
In this article, the authors derived an upper bound on the local Rademacher complexity of multiple kernel learning, which yields a tighter excess risk bound than global approaches, and derived consequences regarding excess loss, namely fast convergence rates of the order O(n^{-\frac{\alpha}{1+\alpha}) where α is the minimum eigenvalue decay rate of individual kernels.Abstract:
We derive an upper bound on the local Rademacher complexity of $\ell_p$-norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches aimed at analyzed the case $p=1$ only while our analysis covers all cases $1\leq p\leq\infty$, assuming the different feature mappings corresponding to the different kernels to be uncorrelated. We also show a lower bound that shows that the bound is tight, and derive consequences regarding excess loss, namely fast convergence rates of the order $O(n^{-\frac{\alpha}{1+\alpha}})$, where $\alpha$ is the minimum eigenvalue decay rate of the individual kernels.read more
Citations
More filters
Posted Content
A Survey on Multi-view Learning
Chang Xu,Dacheng Tao,Chao Xu +2 more
TL;DR: By exploring the consistency and complementary properties of different views, multi-View learning is rendered more effective, more promising, and has better generalization ability than single-view learning.
Journal ArticleDOI
Multiview Consensus Graph Clustering
TL;DR: A multiview consensus clustering method to learn a consensus graph with minimizing disagreement between different views and constraining the rank of the Laplacian matrix is proposed.
Posted Content
Audio-Visual Instance Discrimination with Cross-Modal Agreement
TL;DR: It is shown that optimizing for cross-modal discrimination, rather than within-modAL discrimination, is important to learn good representations from video and audio, and this self-supervised learning approach achieves highly competitive performance when finetuned on action recognition tasks.
Journal ArticleDOI
Sparsity in multiple kernel learning
Vladimir Koltchinskii,Ming Yuan +1 more
TL;DR: The goal is to establish oracle inequalities for the excess risk of the resulting prediction rule showing that the method is adaptive both to the unknown design distribution and to the sparsity of the problem.
Journal ArticleDOI
Graph Structure Fusion for Multiview Clustering
TL;DR: The proposed method is based on the assumption that the intrinsic underlying graph structure would assign corresponding connected component in each graph to the same cluster, and obtains better clustering performance than the state-of-the-art methods.
References
More filters
Journal ArticleDOI
Support-Vector Networks
Corinna Cortes,Vladimir Vapnik +1 more
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Journal ArticleDOI
Nonlinear component analysis as a kernel eigenvalue problem
TL;DR: A new method for performing a nonlinear form of principal component analysis by the use of integral operator kernel functions is proposed and experimental results on polynomial feature extraction for pattern recognition are presented.
Journal ArticleDOI
Minds, brains, and programs
TL;DR: Only a machine could think, and only very special kinds of machines, namely brains and machines with internal causal powers equivalent to those of brains, and no program by itself is sufficient for thinking.
Book
Minds, Brains, and Programs
TL;DR: In this article, the main argument of this paper is directed at establishing this claim and the form of the argument is to show how a human agent could instantiate the program and still not have the relevant intentionality.
Journal ArticleDOI
An introduction to kernel-based learning algorithms
TL;DR: This paper provides an introduction to support vector machines, kernel Fisher discriminant analysis, and kernel principal component analysis, as examples for successful kernel-based learning methods.