IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation.
Taejong JooDiego KlabjanPublished in: CoRR (2023)
Keyphrases
- model selection
- parameter estimation
- leave one out cross validation
- error estimation
- cross validation
- hyperparameters
- selection criterion
- sample size
- statistical learning
- bayesian learning
- regression model
- motion segmentation
- mixture model
- information criterion
- model selection criteria
- meta learning
- variable selection
- machine learning
- feature selection
- gaussian process
- bayesian methods
- hypothesis tests
- statistical inference
- parameter determination
- bayesian information criterion
- missing data
- training data
- automatic model selection