Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML
Mustafa Cavus, Jan N. van Rijn, PrzemysÅaw Biecek
Automated machine learning systems efficiently streamline model selection but often focus on a single best-performing model, overlooking explanation uncertainty, an essential conce…
cs.LG2025
The Role of Hyperparameters in Predictive Multiplicity
Mustafa Cavus, Katarzyna Woźnica, PrzemysÅaw Biecek
This paper investigates the critical role of hyperparameters in predictive multiplicity, where different machine learning models trained on the same dataset yield divergent predict…
cs.LG2024
An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification
Mustafa Cavus, PrzemysÅaw Biecek
Predictive models may generate biased predictions when classifying imbalanced datasets. This happens when the model favors the majority class, leading to low performance in accurat…