Search Results for author:
Found 4 papers, 3 papers with code
On the Richness of Calibration
We demonstrate that with appropriate choices of grouping, these novel global fairness scores can provide notions of (sub-)group or individual fairness.
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
But most computation and time is wasted on redundant and noisy points that are already learnt or not learnable.
Encoding Causal Macrovariables
In a synthetic dataset, the algorithm robustly detects the ground-truth variables and correctly infers the causal relationships between them.
DeDUCE: Generating Counterfactual Explanations Efficiently
This is the aim of algorithms generating counterfactual explanations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
