2 papers
stat.ML2025
Quasiprobabilistic Density Ratio Estimation with a Reverse Engineered Classification Loss Function
Matthew Drnevich, Stephen Jiggins, Kyle Cranmer
We consider a generalization of the classifier-based density-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative. The problem with mos…
stat.ML2024
Neural Quasiprobabilistic Likelihood Ratio Estimation with Negatively Weighted Data
Matthew Drnevich, Stephen Jiggins, Judith Katzy +1
Motivated by real-world situations found in high energy particle physics, we consider a generalisation of the likelihood-ratio estimation task to a quasiprobabilistic setting where…