Quantity vs Quality: Investigating the Trade-Off between Sample Size and Label Reliability.
Timo BertramJohannes FürnkranzMartin MüllerPublished in: CoRR (2022)
Keyphrases
- sample size
- trade off
- model selection
- random sampling
- small sample size
- upper bound
- covariance matrix
- statistical power
- small sample
- pac learning
- statistical tests
- experimental design
- worst case
- confidence intervals
- multi label
- vc dimension
- generalization error
- random sample
- small samples
- machine learning
- hypothesis tests
- high dimensional
- lower bound
- variance reduction
- class labels
- number of training samples
- data sets
- statistical hypothesis testing
- progressive sampling