Learning with many experts: model selection and sparsity
From MaRDI portal
Abstract: Experts classifying data are often imprecise. Recently, several models have been proposed to train classifiers using the noisy labels generated by these experts. How to choose between these models? In such situations, the true labels are unavailable. Thus, one cannot perform model selection using the standard versions of methods such as empirical risk minimization and cross validation. In order to allow model selection, we present a surrogate loss and provide theoretical guarantees that assure its consistency. Next, we discuss how this loss can be used to tune a penalization which introduces sparsity in the parameters of a traditional class of models. Sparsity provides more parsimonious models and can avoid overfitting. Nevertheless, it has seldom been discussed in the context of noisy labels due to the difficulty in model selection and, therefore, in choosing tuning parameters. We apply these techniques to several sets of simulated and real data.
Recommendations
- New estimation and feature selection methods in mixture-of-experts models
- Regression learning with multiple noisy oracles
- Regularized estimation and feature selection in mixtures of experts
- Learning kernel logistic regression in the presence of class label noise
- SELECTING AMONGST LARGE CLASSES OF MODELS
Cites work
Cited in
(5)- Regression learning with multiple noisy oracles
- Prior shift using the ratio estimator
- A comparison of two methods for obtaining a collective posterior distribution
- Quantification under prior probability shift: the ratio estimator and its extensions
- Teaching Decision Theory Proof Strategies Using a Crowdsourcing Problem
This page was built for publication: Learning with many experts: model selection and sparsity
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2870765)
