Search Results for author:
Found 7 papers, 2 papers with code
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
Class distribution shifts are particularly challenging for zero-shot classifiers, which rely on representations learned from training classes but are deployed on new, unseen ones.
Confident Feature Ranking
We propose a novel method for the post-hoc interpretation of feature importance values that is based on the framework and pairwise comparisons of the feature importance values.
Logistic Regression Equivalence: A Framework for Comparing Logistic Regression Models Across Populations
We develop a cascading set of equivalence tests, in which each test addresses a different aspect of the model: the way the phenomenon is coded in the regression coefficients, the individual predictions in the per example log odds ratio and the overall accuracy in the mean square prediction error.
Predicting Classification Accuracy When Adding New Unobserved Classes
We show that the classification accuracy is a function of the rROC in multiclass classifiers, for which the learned representation of data from the initial class sample remains unchanged when new classes are added.
Extrapolating Expected Accuracies for Large Multi-Class Problems
The difficulty of multi-class classification generally increases with the number of classes.
How many faces can be recognized? Performance extrapolation for multi-class classification
Using data from a subset of the classes, can we predict how well a classifier will scale with an increased number of classes?
Estimating mutual information in high dimensions via classification error
Multivariate pattern analyses approaches in neuroimaging are fundamentally concerned with investigating the quantity and type of information processed by various regions of the human brain; typically, estimates of classification accuracy are used to quantify information.
