DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection.
Jaemin YooYue ZhaoLingxiao ZhaoLeman AkogluPublished in: CoRR (2023)
Keyphrases
- model selection
- cross validation
- hyperparameters
- regression model
- sample size
- outlier detection
- bayesian learning
- mixture model
- statistical learning
- parameter estimation
- machine learning
- feature selection
- meta learning
- bayesian methods
- error estimation
- information criterion
- variable selection
- gaussian process
- statistical inference
- motion segmentation
- selection criterion
- model selection criteria
- generalization bounds
- generalization error
- support vector
- training data
- bayesian information criterion
- multivariate regression