Estimation of squared-loss mutual information from paired and unpaired samples (情報論的学習理論と機械学習)
スポンサーリンク
概要
- 論文の詳細を見る
Mutual information (MI) is a measure of statistical dependence between random variables and is usually estimated from samples drawn from the joint distribution (i.e., paired samples). However, collecting paired samples is often costly in practice and therefore obtaining an accurate estimator of MI is a fundamental challenge in machine learning. In this paper, we propose to use unpaired samples drawn from the marginal distributions in MI estimation. More specifically, we extend least-squares mutual information (LSMI), which is an estimator of a squared-loss variant of MI with the optimal convergence rate, so that unpaired samples can effectively be incorporated. We demonstrate the effectiveness of the proposed method, called unpaired LSMI, in experiments on sufficient dimension reduction and independence testing.
- 2011-06-13
著者
-
Yamada Makoto
Department Of Chemistry Faculty Of Science Okayama University Of Science
-
Sugiyama Masashi
Department Of Computer Science Tokyo Institute Of Technology
-
Du Plessis
Department Of Botany And Genetics University Of The Orange Free State
-
Du Plessis
Department Of Computer Science Tokyo Institute Of Technology
-
Yamada Makoto
Department Of Chemistry And Biomolecular Science Toho University
-
Sugiyama Masashi
Department Of Chemistry Faculty Of Science Tokyo University Of Science
関連論文
- Statistical active learning for efficient value function approximation in reinforcement learning (ニューロコンピューティング)
- Improving the Accuracy of Least-Squares Probabilistic Classifiers
- Improving the Accuracy of Least-Squares Probabilistic Classifiers
- A New Meta-Criterion for Regularized Subspace Information Criterion
- Approximating the Best Linear Unbiased Estimator of Non-Gaussian Signals with Gaussian Noise
- A new algorithm of non-Gaussian component analysis with radial kernel functions (Special issue: Information geometry and its applications)
- Spontaneous Rupture of the Iliac Vein : Report of a Case
- Methods of cross-domain object matching (情報論的学習理論と機械学習)
- Conjugation of Laminin Derived Cell Adhesive Peptides on a Chitosan Membrane and Their Biological Activity
- Screening of Amyloidogenic Peptides in Laminin-1
- Multifunctional Peptide-Chitosan Membrane : New Biomedical Materials
- γ-Functional Prolines Based on Naturally Occurred Hydroxyproline. III
- Accumulation-Exclusion Combined System for the DNA-Binding Harmful Chemicals with Insolubilized DNA
- UV-Irradiated DNA Matrix Selectively Accumulates Heavy Metal Ions
- Effect of Nucleoplasmin on a Nucleosome Structure
- Neurite Outgrowth Promoting Sites on the Laminin Alpha 3 Chain
- Cell Adhesive and Heparin Binding Sites on the Laminin Alpha Chain G Domains
- γ-Functional Prolines Based on Naturally Occurring Hydroxyproline. II
- Identification of Biologically Active Sequences on the Laminin Alpha Chain G Domains
- Identification of Cell Adhesive Sites on the Laminin Alpha Chain Domain VI
- Multi-task learning with least-squares probabilistic classifiers (パターン認識・メディア理解)
- Multi-task learning with least-squares probabilistic classifiers (情報論的学習理論と機械学習)
- Adaptive importance sampling with automatic model selection in value function approximation (ニューロコンピューティング)
- Analytic Optimization of Adaptive Ridge Parameters Based on Regularized Subspace Information Criterion(Neural Networks and Bioengineering)
- Adaptive Ridge Learning in Kernel Eigenspace and Its Model Selection
- On Computational Issues of Semi-Supervised Local Fisher Discriminant Analysis
- Myonase is Localized in Skeletal Muscle Myofibrils
- Recent Advances and Trends in Large-Scale Kernel Methods
- Covered Stent Treatment for Traumatic Cervical Carotid Artery Aneurysms : Two Case Reports
- Syntheses of New Artificial Zinc Finger Proteins Containing Trisbipyridine-ruthenium Amino Acid at The N-or C-terminus as Fluorescent Probes
- Practical Synthesis of 4-cis Hydroxy-L-Proline
- Ovarian Histological Findings in an Adult Patient with the Steroidogenic Acute Regulatory Protein (StAR) Deficiency Reveal the Impairment of Steroidogenesis by Lipoid Deposition
- Analytic Optimization of Shrinkage Parameters Based on Regularized Subspace Information Criterion(Neural Networks and Bioengineering)
- Constructing Kernel Functions for Binary Regression(Pattern Recognition)
- Optimal design of regularization term and regularization parameter by subspace information criterion
- Solid-papillary carcinoma of the breast : Clinicopathological study of 20 cases
- A fast sequence kernel for sequential data classification (Speech) -- (国際ワークショップ"Asian workshop on speech science and technology")
- Information-maximization clustering: analytic solution and model selection (情報論的学習理論と機械学習)
- New feature selection method for reinforcement learning: conditional mutual information reveals implicit state-reward dependency (情報論的学習理論と機械学習)
- Least Absolute Policy Iteration-A Robust Approach to Value Function Approximation
- Independent component analysis by direct density-ratio estimation (ニューロコンピューティング)
- A New Meta-Criterion for Regularized Subspace Information Criterion(Pattern Recognition)
- Spectral Methods for Thesaurus Construction
- Adaptive importance sampling with automatic model selection in reward weighted regression (ニューロコンピューティング)
- SERAPH: semi-supervised metric learning paradigm with hyper sparsity (情報論的学習理論と機械学習)
- Analysis and improvement of policy gradient estimation (情報論的学習理論と機械学習)
- Direct density-ratio estimation with dimensionality reduction via hetero-distributional subspace analysis (情報論的学習理論と機械学習)
- Output divergence criterion for active learning in collaborative settings (数理モデル化と問題解決・バイオ情報学)
- Estimation of squared-loss mutual information from paired and unpaired samples (情報論的学習理論と機械学習)
- Dependence minimizing regression with model selection for non-linear causal inference under non-Gaussian noise (情報論的学習理論と機械学習)
- Canonical dependency analysis based on squared-loss mutual information (情報論的学習理論と機械学習)
- Artist agent A[2]: stroke painterly rendering based on reinforcement learning (パターン認識・メディア理解)
- Artist agent A[2]: stroke painterly rendering based on reinforcement learning (情報論的学習理論と機械学習)
- Generalization Error Estimation for Non-linear Learning Methods(Neural Networks and Bioengineering)
- Improving Precision of the Subspace Information Criterion(Neural Networks and Bioengineering)
- Canonical dependency analysis based on squared-loss mutual information (パターン認識・メディア理解)
- Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation (情報論的学習理論と機械学習)
- Modified Newton Approach to Policy Search (情報論的学習理論と機械学習)
- Computationally Efficient Multi-Label Classification by Least-Squares Probabilistic Classifier (情報論的学習理論と機械学習)
- Relative Density-Ratio Estimation for Robust Distribution Comparison (情報論的学習理論と機械学習)
- Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation
- Modified Newton Approach to Policy Search
- Squared-loss Mutual Information Regularization
- Computationally Efficient Multi-Label Classification by Least-Squares Probabilistic Classifier
- Feature Selection via l_1-Penalized Squared-Loss Mutual Information
- Semi-Supervised Learning of Class Balance under Class-Prior Change by Distribution Matching (情報論的学習理論と機械学習)
- Relative Density-Ratio Estimation for Robust Distribution Comparison
- Prospective Assessment of Pain and Functional Status After Percutaneous Vertebral Body-Perforation Procedure for Treatment of Vertebral Compression Fractures
- Winning the Kaggle Algorithmic Trading Challenge with the Composition of Many Models and Feature Engineering (情報論的学習理論と機械学習)
- Early Stopping Heuristics in Pool-Based Incremental Active Learning for Least-Squares Probabilistic Classifier (情報論的学習理論と機械学習)
- Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration (情報論的学習理論と機械学習)
- Clustering Unclustered Data : Unsupervised Binary Labeling of Two Datasets Having Different Class Balances
- Prospective Assessment of Pain and Functional Status After Percutaneous Vertebral Body-Perforation Procedure for Treatment of Vertebral Compression Fractures