Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Of Dice and Games: A Theory of Generalized Boosting
Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi +4
Cost-sensitive loss functions are crucial in many real-world prediction problems, where different types of errors are penalized differently; for example, in medical diagnosis, a fa…
cs.LG2024
Efficient Algorithms for Learning Monophonic Halfspaces in Graphs
Marco Bressan, Emmanuel Esposito, Maximilian Thiessen
We study the problem of learning a binary classifier on the vertices of a graph. In particular, we consider classifiers given by monophonic halfspaces, partitions of the vertices t…
cs.LG2024
A Theory of Interpretable Approximations
Marco Bressan, Nicolò Cesa-Bianchi, Emmanuel Esposito +3
Can a deep neural network be approximated by a small decision tree based on simple features? This question and its variants are behind the growing demand for machine learning model…