Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation

DOI10.1162/NECO_a_00407zbMath1269.62054WikidataQ50767941 ScholiaQ50767941MaRDI QIDQ5327187

Masashi Sugiyama, Taiji Suzuki

Publication date: 7 August 2013

Published in: Neural Computation (Search for Journal in Brave)

Mathematics Subject Classification ID

Multivariate analysis (62H99) Asymptotic properties of nonparametric inference (62G20)

Related Items (16)

A brief review of linear sufficient dimension reduction through optimization ⋮ Manifold Optimization-Assisted Gaussian Variational Approximation ⋮ Canonical kernel dimension reduction ⋮ Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models ⋮ Semi-supervised information-maximization clustering ⋮ Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation ⋮ Density-Difference Estimation ⋮ Conditional Density Estimation with Dimensionality Reduction via Squared-Loss Conditional Entropy Minimization ⋮ Direct Estimation of the Derivative of Quadratic Mutual Information with Application in Supervised Dimension Reduction ⋮ Wasserstein discriminant analysis ⋮ Least-squares independence regression for non-linear causal inference under non-Gaussian noise ⋮ Supervised dimensionality reduction via distance correlation maximization ⋮ Sufficient Dimension Reduction via Direct Estimation of the Gradients of Logarithmic Conditional Densities ⋮ Dimensionality reduction for density ratio estimation in high-dimensional spaces ⋮ Model-based reinforcement learning with dimension reduction ⋮ Information-Theoretic Representation Learning for Positive-Unlabeled Classification

Cites Work

• Unnamed Item
• A constructive approach to the estimation of dimension reduction directions
• Fast rates for support vector machines using Gaussian kernels
• Rates of convergence for minimum contrast estimators
• Dual representation of \(\phi\)-divergences and applications.
• Sufficient dimension reduction and graphics in regression
• Kernel dimension reduction in regression
• 10.1162/153244302760185252
• Functional Principal Component Regression and Functional Partial Least Squares
• Estimating Optimal Transformations for Multiple Regression and Correlation
• Sliced Inverse Regression for Dimension Reduction
• Asymptotic Statistics
• The Geometry of Algorithms with Orthogonality Constraints
• Extending Sliced Inverse Regression
• Save: a method for dimension reduction and graphics in regression
• Estimation of the information by an adaptive partitioning of the observation space
• 10.1162/153244302760200687
• 10.1162/153244303322753742
• Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
• Probability Inequalities for Sums of Bounded Random Variables
• Elements of Information Theory
• Edgeworth Approximation of Multivariate Differential Entropy
• Sufficient Dimension Reduction via Inverse Regression
• On Sliced Inverse Regression With High-Dimensional Covariates
• RELATIONS BETWEEN TWO SETS OF VARIATES
• A Class of Statistics with Asymptotically Normal Distribution
• Theory of Reproducing Kernels
• On Information and Sufficiency
• A new look at the statistical model identification

This page was built for publication: Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation