Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
From MaRDI portal
Abstract: Methods for analyzing or learning from "fuzzy data" have attracted increasing attention in recent years. In many cases, however, existing methods (for precise, non-fuzzy data) are extended to the fuzzy case in an ad-hoc manner, and without carefully considering the interpretation of a fuzzy set when being used for modeling data. Distinguishing between an ontic and an epistemic interpretation of fuzzy set-valued data, and focusing on the latter, we argue that a "fuzzification" of learning algorithms based on an application of the generic extension principle is not appropriate. In fact, the extension principle fails to properly exploit the inductive bias underlying statistical and machine learning methods, although this bias, at least in principle, offers a means for "disambiguating" the fuzzy data. Alternatively, we therefore propose a method which is based on the generalization of loss functions in empirical risk minimization, and which performs model identification and data disambiguation simultaneously. Elaborating on the fuzzification of specific types of losses, we establish connections to well-known loss functions in regression and classification. We compare our approach with related methods and illustrate its use in logistic regression for binary classification.
Recommendations
- Comments on ``Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
- Comments on ``Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
- Rejoinder on ``Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
- Learning from ambiguous and misspecified models
- Advances in Intelligent Data Analysis VI
- Learning fuzzy measures from data: simplifications and optimisation strategies
Cites work
- A linear regression model for imprecise response
- Estimation of a simple linear regression model for fuzzy random variables
- Fuzzy least squares
- Fuzzy random variables
- Fuzzy random variables - I. Definitions and theorems
- Fuzzy random variables - II. Algorithms and examples for the discrete case
- Gradual elements in a fuzzy set
- scientific article; zbMATH DE number 1302079 (Why is no real title available?)
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- Improving predictive inference under covariate shift by weighting the log-likelihood function
- Learning from partial labels
- Learning from partially supervised data using mixture models and belief functions
- Maximum likelihood estimation from fuzzy data using the EM algorithm
- Possibilistic data analysis for operations research
- Robust Statistics
- Statistical methods for fuzzy data
- Statistics with vague data
- The concept of a linguistic variable and its application to approximate reasoning. III
- Towards fast and accurate algorithms for processing fuzzy data: interval computations revisited
Cited in
(43)- Partial data querying through racing algorithms
- Online active learning of decision trees with evidential data
- On the testability of coarsening assumptions: a hypothesis test for subgroup independence
- A new framework for the statistical analysis of set-valued random elements
- A framework for learning fuzzy rule-based models with epistemic set-valued data and generalized loss functions
- Clustering and classification of fuzzy data using the fuzzy EM algorithm
- A general framework for maximizing likelihood under incomplete data
- Ground truthing from multi-rater labeling with three-way decision and possibility theory
- Interval-valued kriging for geostatistical mapping with imprecise inputs
- Cautious classification based on belief functions theory and imprecise relabelling
- Belief functions and rough sets: survey and new insights
- Racing trees to query partial data
- A min-max regret approach to maximum likelihood inference under incomplete data
- From fuzzy regression to gradual regression: interval-based analysis and extensions
- Instance weighting through data imprecisiation
- Rough set-based feature selection for weakly labeled data
- Machine learning models, epistemic set-valued data and generalized loss functions: an encompassing approach
- The three-way-in and three-way-out framework to treat and exploit ambiguity in data
- Fuzziness in data analysis: towards accuracy and robustness
- Binary classification SVM-based algorithms with interval-valued training data using triangular and Epanechnikov kernels
- Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression
- Harnessing the information contained in low-quality data sources
- On various ways of tackling incomplete information in statistics
- Comments on ``Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
- Rejoinder on ``Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
- Feature selection and disambiguation in learning from fuzzy labels using rough sets
- Cautious label ranking with label-wise decomposition
- Statistical modeling under partial identification: distinguishing three types of identification regions in regression analysis with interval data
- Belief revision and the EM algorithm
- Independent \(k\)-sample equality distribution test based on the fuzzy representation
- Comments on ``Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
- Reliable Inference in Categorical Regression Analysis for Non‐randomly Coarsened Observations
- Algorithm selection on a meta level
- Three-way decision and conformal prediction: isomorphisms, differences and theoretical properties of cautious learning approaches
- Levelwise data disambiguation by cautious superset classification
- Learning from fuzzy labels: theoretical issues and algorithmic solutions
- Synergies between machine learning and reasoning -- an introduction by the Kay R. Amel group
- Preference learning and multiple criteria decision aiding: differences, commonalities, and synergies. II
- Maximum likelihood probability measures over sets: existence, computation, and convergence
- Robustifying Likelihoods by Optimistically Re-weighting Data
- Fuzzy neighborhood-based partial label feature selection via label iterative disambiguation
- Fuzzy neighborhood components analysis: supervised dimensionality reduction under uncertain labels
- Thomas Augustin's contributions to imprecise probability and statistics
This page was built for publication: Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2509600)
