Feature Selection via Dependence Maximization

By Le Song, Alex Smola, Arthur Gretton, Justin Bedo, Karsten M. Borgwardt. 2012

477 citations recorded by the source corpus.

How researchers see this paper

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

In Optimization & Training

Citations in the corpus

Minimax Estimation of Kernel Mean Embeddings (2016, background): “, 2007), density estimation (Sriperumbudur, 2011), feature selection (Song et al., 2012), causal inference (Lopez-Paz et al.”
Distinguishing Cause from Effect Using Observational Data: Methods and Benchmarks (2014, background): “Unbiased estimators of the population HSIC were proposed in later work (Song et al., 2012), but we will not consider those here.”
A low variance consistent test of relative dependency (2014, methodology): “M L ] 1 variables and the source is computed using the Hilbert-Schmidt Independence Criterion [4, 5].”
Nonparametric Independence Testing for Small Sample Sizes (2014, methodology): “The long list of applications includes kernel PCA [1], dimension reduction [2], structure discovery [3], independence testing [4], Granger causality in time series [5], learning graphical models [6], feature learning [7], target or conditional shift [8] and kernel Bayes’ rule [9].”
A Kernel Independence Test for Random Processes (2014, background): “Measures of statistical dependence between pairs of random variables (X,Y ) are well established, and have been applied in a wide variety of areas, including fitting causal networks (Pearl, 2000), discovering features which have significant dependence on a label set (Song et al., 2012), and independ”
Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences (2018, methodology): “Since it also can be calculated in a simple way using kernels, it has found a wide range of applications including independence testing [Gretton et al., 2008, Zhang et al., 2018], variable selection [Song et al., 2012, Yamada et al., 2014], post selection inference [Yamada et al., 2018], and causal ”
Gradient boosted feature selection (2014, background): “H.3 [Information Storage and Retrieval]: Miscellaneous; I.5.2 [Pattern Recognition]: Design Methodology—Feature evaluation and selection”
Feature selection based on mutual information (2015, methodology): “Also, two different aging databases were used in [16] for experiment.”
On Similarity Preserving Feature Selection (2013, methodology): “It is shown in [36] that when a linear kernel is used to compute the K F in (2.4), the HSIC criterion can be formulated as When a nonlinear kernel function is used for constructing K F , features’ contribution to K F cannot be simply decomposed as in the linear kernel case.”
High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso (2012, methodology): “…existing feature selection approaches such as minimum redundancy maximum relevance (mRMR) (Peng et al. , 2005), HSIC-based greedy feature selection (Song et al. , 2012), quadratic programming feature selection (QPFS) (Rodriguez-Lujan et al. , 2010), kernel target alignment (KTA) (Shawe-Taylor and…”
A review of microarray datasets and applied feature selection methods (2014, methodology): “Ovarian 253 15,154 36–64% [93] 2002 [24,25,23,27,120,107] [8] Prostate 102 6033 51–49% [106] 2002 [78,11] unknown”
An Updated Literature Review of Distance Correlation and Its Applications to Time Series (2017, background): “In particular, Székely and Rizzo (2014) show thatR(X,Y ;Z) = 0 is not equivalent to conditional independence of X and Y given Z .”
Large-scale kernel methods for independence testing (2016, background): “2007; Blaschko and Gretton 2009), feature selection (Song et al. 2012), causal inference (Peters et al.”
Feature selection for high-dimensional class-imbalanced data sets using Support Vector Machines (2014, methodology): “Following the notation used by Song et al. [31], we denote by S the full set of features.”
From Dependence to Causation (2016, methodology): “We performed greedy feature selection via dependence maximization (Song et al., 2012) on real-world datasets.”
Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth (2020, methodology): “This approach of estimating HSIC on minibatches is equivalent to the bagging block HSIC approach of Yamada et al. (2018).”