Complexity Measures of Supervised Classification Problems

By Kam Ho, Mitra Basu

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Adarsh Subbaswamy
2. Suchi Saria
3. Ioana Bica
4. Bernhard Schölkopf
5. Peter F. Schulam
6. Ahmed M. Alaa
7. Mihaela van der Schaar

Citations in the corpus

• Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms (2018, methodology): “To measure classifier-independent geometric complexity we will use two types of metrics developed by Ho and Basu (2000, 2002): measures of overlap of individual features and measures of separability of classes.”
• Meta-Learning: A Survey (2018, neutral): “Separability classes c 1 ,c 2 [64] See [64] Volume of overlap Class distribution overlap [64] See [64]”