Speaker
Malte Algren
(Universite de Geneve (CH))
Description
Novel decorrelation method using Convex Neural Optimal Transport Solvers (Cnots) that is able to decorrelate a continuous feature space against protected attributes with optimal transport. We demonstrate how well it performs in the context of jet classification in high energy physics, where classifier scores are desired to be decorrelated from the mass of a jet.
Brainstorming idea [abstract]
The paper: "Robust and Provably Monotonic Networks" showed how monotonic networks could be used in HEP. Would be interesting to see if this could be extended to other architectures and data structures.
| Brainstorming idea [title] | Monotonic neural networks to avoid overfitting |
|---|
Primary authors
Johnny Raine
(Universite de Geneve (CH))
Malte Algren
(Universite de Geneve (CH))
Tobias Golling
(Universite de Geneve (CH))
