Information Geometry of U-Boost and Bregman Divergence

DOI10.1162/089976604323057452zbMATH Open1102.68489DBLPjournals/neco/MurataTKE04OpenAlexW2106579555WikidataQ51670214 ScholiaQ51670214MaRDI QIDQ4832497FDOQ4832497

Authors: Noboru Murata, Takashi Takenouchi, Takafumi Kanamori, Shinto Eguchi 

Publication date: 4 January 2005

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

Full work available at URL: https://doi.org/10.1162/089976604323057452

Recommendations

• Information geometry and statistical pattern recognition
• Logistic regression, AdaBoost and Bregman distances
• Tutorial series on brain-inspired computing. VI: Geometrical structure of boosting algorithm
• Boosting. Foundations and algorithms.
• A Bregman extension of quasi-Newton updates I: An information geometrical framework

zbMATH Keywords

learning machinesclassification machine

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32)

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• Robust Blind Source Separation by Beta Divergence
• Robustifying AdaBoost by Adding the Naive Error Rate

Cited In (48)

• Variational representations of annealing paths: Bregman information under monotonic embedding
• Robust Boosting Algorithm Against Mislabeling in Multiclass Problems
• A Bregman extension of quasi-Newton updates I: An information geometrical framework
• A Novel Parameter Estimation Method for Boltzmann Machines
• Conformal mirror descent with logarithmic divergences
• Geometry of EM and related iterative algorithms
• Information Divergence Geometry and the Application to Statistical Machine Learning
• Kernel density estimation by stagewise algorithm with a simple dictionary
• Density estimation with minimization of \(U\)-divergence
• Some universal insights on divergences for statistics, machine learning and artificial intelligence
• The geometry of proper scoring rules
• Projections with logarithmic divergences
• Ternary Bradley-Terry model-based decoding for multi-class classification and its extensions
• Entropic risk minimization for nonparametric estimation of mixing distributions
• Nonparametric information geometry: from divergence function to referential-representational biduality on statistical manifolds
• Statistical learning for species distribution models in ecological studies
• A Bregman extension of quasi-Newton updates. II: Analysis of robustness properties
• Robust parameter estimation with a small bias against heavy contamination
• Integration of Stochastic Models by Minimizing α-Divergence
• Tutorial series on brain-inspired computing. VI: Geometrical structure of boosting algorithm
• Normalized estimating equation for robust parameter estimation
• Binary classification with a pseudo exponential model and its application for multi-task learning
• Deformed algebras and generalizations of independence on deformed exponential families
• Duality of maximum entropy and minimum divergence
• Statistical analysis of distance estimators with density differences and density ratios
• Minimum Divergence Methods in Statistical Machine Learning
• Information geometry approach to parameter estimation in hidden Markov model
• Entropy and divergence associated with power function and the statistical application
• A Note on Divergences
• A modified EM algorithm for mixture models based on Bregman divergence
• Re-examination of Bregman functions and new properties of their divergences
• Information geometry and statistical pattern recognition
• Affine invariant divergences associated with proper composite scoring rules and their applications
• Boosting Method for Local Learning in Statistical Pattern Recognition
• Dually flat geometries of the deformed exponential family
• A new integrated discrimination improvement index via odds
• A boosting method with asymmetric mislabeling probabilities which depend on covariates
• Graph-based composite local Bregman divergences on discrete sample spaces
• An extension of the receiver operating characteristic curve and AUC-optimal classification
• Robust Loss Functions for Boosting
• Deformation of log-likelihood loss function for multiclass boosting
• Hessian structures on deformed exponential families and their conformal structures
• A Multiclass Classification Method Based on Decoding of Binary Classifiers
• Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation
• Interpreting Kullback--Leibler divergence with the Neyman-Pearson Lemma
• An estimation of generalized Bradley-Terry models based on the EM algorithm
• Improved estimators of Bregman divergence for model selection in small samples
• A boosting method for maximization of the area under the ROC curve

This page was built for publication: Information Geometry of U-Boost and Bregman Divergence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4832497)