Using labeled data to evaluate change detectors in a multivariate streaming environment

By Albert Y. Kim, Caren Marzban, Donald B. Percival, Werner Stuetzle. 2009

2,818 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 Statistics and Probability

Citations in the corpus

Are Disentangled Representations Helpful for Abstract Visual Reasoning? (2019, background): “Other Related Works Learning disentangled representations is similar in spirit to non-linear ICA, although it relies primarily on (architectural) inductive biases and different degrees of supervision [13, 2, 39, 36, 37, 38, 25, 33, 32].”
The Incomplete Rosetta Stone problem: Identifiability results for Multi-view Nonlinear ICA (2019, background): “A simple case in which the assumption does not hold is when the conditional probability of z given s is Gaussian, as in where Z is the normalization factor, Z = (2 π ) n/ 2 i σ i .”
The Arrow of Time in Multivariate Time Series (2016, methodology): “ but not all innovations are non-Gaussian is not covered. Both proofs can be found in Section 6. The Darmois-Skitovic theorem is used for proving the identiability of independent component analysis (Comon, 1994) and lies at the heart of the proof of Theorem 4. Lemma 5 (Vectorised Darmois-Skitovich t”
Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning (2018, background): “Proving the identifiability of linear ICA (Comon, 1994) was a great advance on the classical theory of factor analysis, where an orthogonal factor rotation could not be”
Sampling Matters in Deep Embedding Learning (2017, neutral): “Convex approaches were much more popular [7, 39].”
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN) (2020, methodology): “The task of nonlinear ICA is to disentangle the data to recover the generating latent variables z, as well as the form of the function f and its inverse.”
THE THREE EASY ROUTES TO INDEPENDENT COMPONENT ANALYSIS; CONTRASTS AND GEOMETRY (2001, neutral): “case, Comon had already noticed in his seminal paper [4], that if one enforces decorrelation, (that is, C(Y ) = 0), then the mutual information boils down to the sum of the marginal ‘neguentropies’.”
Fusing Gabor and LBP Feature Sets for Kernel-Based Face Recognition (2007, methodology): “Many dimensionality reduction techniques could be considered – Principal Component Analysis (PCA) [8], Independent Component Analysis (ICA) [20], Non-negative Matrix Factorization (NMF) [14], and Canonical Correlation Analysis (CCA) [13] to mention only some of the linear ones – but here we find tha”
Source separation in post-nonlinear mixtures (1999, methodology): “This kind of expansion has already been used by Comon [8] and Gaeta et al. [14] in the linear case and by Taleb and Jutten [34] and Yang et al. [39] in the nonlinear source separation case.”
Does independent component analysis play a role in unmixing hyperspectral data? (2003, methodology): “objective function used in ICA algorithms is the mutual information [ 28 ] of vector”
Sibe: a computation tool to apply protein sequence statistics to predict folding and design in silico (2019, background): “(3) between pairs of amino acids by independent component (IC) analysis [41].”
The Why and How of Nonnegative Matrix Factorization (2014, background): “For example, assuming independence of the columns of W leads to independent component analysis (ICA) [29], or assuming sparsity of W (and/or H ) leads to sparse low-rank matrix decompositions, such as sparse PCA [32].”
Rethinking LDA: Moment Matching for Discrete ICA (2015, neutral): “In this paper, we draw explicit links with the independent component analysis (ICA) literature (e.g., [5] and references therein) by showing a strong relationship between latent Dirichlet allocation (LDA) [1] and ICA [6, 7, 8].”
Principal Manifolds and Probabilistic Subspaces for Visual Recognition (2002, methodology): “2.2 Linear ICA Manifolds Independent Component Analysis (ICA) [20], [ 9 ] is similar to PCA except that the distribution of the components are designed to be sub/super Gaussian (usually by minimizing/maximizing fourth-order distribution cumulants such as kurtosis).”
Independent component analysis of Gabor features for face recognition (2003, background): “ICA has emerged recently as one powerful solution to the problem of blind source separation [5], [18], [16], while its possible use for face recognition has been shown in [2], [8] by using a neural network approximation.”
A Hilbert Space Embedding for Distributions (2007, background): “One application is in independent component analysis [40], where the goal is to find a linear mapping of the observations xi to obtain mutually independent outputs.”