← Back to all news
arXiv Machine Learning By Johannes Erdmann, Nitish Kumar Kasaraguppe, Florian Mausolf

Learning to bin: differentiable and Bayesian optimization for multi-dimensional discriminants in high-energy physics

Read the original on arXiv Machine Learning →

The paper introduces a method for optimizing bin boundaries in multi-dimensional discriminants using a Gaussian Mixture Model (GMM), allowing flexible definition of analysis categories. Two optimization strategies—differentiable and Bayesian—are compared in toy binary and three-class setups, with the differentiable approach excelling in multi-dimensional cases. Applied to the FAIR Universe $H ightarrow au au$ dataset, the GMM-based optimization achieves the highest signal significance, and the tools are released as lightweight Python plugins.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 27

Multi-output Gaussian process prediction of physical fields under linear equality constraints

The paper tackles the challenge of predicting multiple high‑dimensional physical fields that must satisfy linear equality constraints, a common scenario in physics‑informed machine learning. It critiques the conventional approach of deducing one field from others, showing its sensitivity to arbitrary choices and its impact on accuracy and uncertainty. To address this, the authors introduce a symmetric framework that first applies a row‑wise PCA to preserve constraints in a latent space, then trains a linearly‑constrained multi‑output Gaussian process using a specially parametrized kernel, and validate the method on population dynamics and CFD problems involving Reynolds stress tensors.

By Mahamat Hamdan Nassouradine, Cl\'ement Gauchy, Pierre-Emmanuel Angeli, S\'ebastien da Veiga
diffusionbenchmarks
More like this →