A Projection Pursuit Algorithm for Exploratory Data Analysis

By J. Friedman, J. Tukey. 1974

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

Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) (2014, methodology): “[19, 13] proposed solutions based on tree data structure combined with branch and bound space partitioning technique similar to k-d trees [9].”
Kernel methods in machine learning (2007, neutral): “• For Contrast[f,X] = Curtosis[f,X] and F = {〈w,x〉 subject to ‖w‖ ≤ 1}, we have Projection Pursuit (Friedman and Tukey [55] and Huber [72]).”
High-Breakdown Robust Multivariate Methods (2008, methodology): “The Stahel– Donoho estimator measures the outlyingness by looking at all univariate projections of the data and as such is related to projection pursuit methods as studied in Friedman and Tukey (1974), Huber (1985) and Croux and Ruiz-Gazen (2005).”
A Fast Fixed-Point Algorithm for Independent Component Analysis of Complex Valued Signals (2000, methodology): “For a simple proof of this result, see [10, 8].”
Class prediction and discovery using gene microarray and proteomics mass spectroscopy data: curses, caveats, cautions (2003, methodology): “Inspired by the philosophy of projection pursuit (Friedman and Tukey, 1974), which advocates searching for ‘interesting’ directions in the high-dimensional space, we have developed a distance-based mapping method for visualizing high-dimensional patterns and their relative relationships (Somorjai et”
Stochastic Simulation of Patterns Using Distance-Based Pattern Modeling (2010, background): “On the other hand, according to the convolution theorem of Gaussians (Friedman and Tukey, 1974): ∫”
A robustification of independent component analysis (2005, background): “This is related to projection pursuit (Friedman and Tukey [5]).”
Projection Pursuit Multivariate Transform (2014, unknown): “Nonparametric in nature, PPDE is particularly well suited and effective relative to other techniques when applied to complex and/or high dimensional data (Friedman and Tukey 1974; Hwang et al. 1994).”
Quality Metrics in High-Dimensional Data Visualization: An Overview and Systematization (2011, methodology): “The pioneering work of Friedman and Tukey in 1974 with their projection pursuits method [21] introduced the idea.”
Nonlinear Approximation with Dictionaries I. Direct Estimates (2004, unknown): “To avoid confusion with a different notion of “greedy algorithm” [16, 23, 24, 14, 38], we will rather use the notion of thresholding algorithm and define thresholding approximation classes that generalize the “greedy approximation classes” G q (B) that we defined in [18]:”
Iterative Gaussianization: From ICA to Random Rotations (2011, methodology): “As stated above, the aim of Projection Pursuit (PP) techniques [15], [16] is looking for interesting linear projections according to some projection index measuring interestingness, and after, this interestingness is captured by removing it through the appropriate marginal equalization, thus making ”
Invariant co‐ordinate selection (2009, background): “In projection pursuit, we typically seek interesting, usually meaning non-normal, projections of the data; see for example Cook et al. (1993), Friedman and Tukey (1974), Huber (1985) and Jones and Sibson (1987).”
Computational Statistics Handbook with MATLAB (2001, methodology): “Friedman-Tukey Index This projection pursuit index [Friedman and Tukey, 1974] is based on interpoint distances and is calculated using the following”