paper-with-me

홈 › Papers

Kernel Dependence Network

2020-11-04 · Chieh Wu, Aria Masoomi, Arthur Gretton, Jennifer Dy

We propose a greedy strategy to spectrally train a deep network for multi-class classification. Each layer is defined as a composition of linear weights with the feature map of a Gaussian kernel acting as the activation function. At each layer, the linear weights are learned by maximizing the dependence between the layer output and the labels using the Hilbert Schmidt Independence Criterion (HSIC). By constraining the solution space on the Stiefel Manifold, we demonstrate how our network construct (Kernel Dependence Network or KNet) can be solved spectrally while leveraging the eigenvalues to automatically find the width and the depth of the network. We theoretically guarantee the existence of a solution for the global optimum while providing insight into our network's ability to generalize.

📄 PDF Abstract BibTeX arXiv:2011.03320

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-class Classification

Similar Papers 제목 키워드 기반

Learning Deep Kernels for Non-Parametric Independence Testing

2024-09-10 · Nathaniel Xu, Feng Liu, Danica J. Sutherland

The Hilbert-Schmidt Independence Criterion (HSIC) is a powerful tool for nonparametric detection of dependence between random variables. It crucially depends, however, on the selection of reasonable kernels; commonly-use…

On Distance and Kernel Measures of Conditional Independence

2019-12-02 · Tianhong Sheng, Bharath K. Sriperumbudur

Measuring conditional independence is one of the important tasks in statistical inference and is fundamental in causal discovery, feature selection, dimensionality reduction, Bayesian network learning, and others. In thi…

Causal DiscoveryDimensionality Reductionfeature selection

A simpler condition for consistency of a kernel independence test

2015-01-25 · Arthur Gretton

A statistical test of independence may be constructed using the Hilbert-Schmidt Independence Criterion (HSIC) as a test statistic. The HSIC is defined as the distance between the embedding of the joint distribution, and …

The GaussianSketch for Almost Relative Error Kernel Distance

2018-11-09 · Jeff M. Phillips, Wai Ming Tai

We introduce two versions of a new sketch for approximately embedding the Gaussian kernel into Euclidean inner product space. These work by truncating infinite expansions of the Gaussian kernel, and carefully invoking th…

Discussion of `Multiscale Fisher's Independence Test for Multivariate Dependence'

2022-06-22 · Antonin Schrab, Wittawat Jitkrittum, Zoltán Szabó, Dino Sejdinovic 외

We discuss how MultiFIT, the Multiscale Fisher's Independence Test for Multivariate Dependence proposed by Gorsky and Ma (2022), compares to existing linear-time kernel tests based on the Hilbert-Schmidt independence cri…