Differentiable Analysis Blueprint

Session

Technical Landscape

5 Mar 2026, 17:30

4/3-006 - TH Conference Room (CERN)

9. Tooling for Differentiable HEP [10' + 5']

Lino Oscar Gerlach (Princeton University (US))

05/03/2026, 17:30

23. Differentiable Binning Optimization [10' + 5']

Nitish Kasaraguppe (RWTH Aachen (DE))

05/03/2026, 17:45

Categorizing events using discriminant observables is central to many high-energy physics analyses. Yet, bin boundaries are often chosen by hand. A simple, popular choice is to apply argmax projections of multi-class scores and equidistant binning of one-dimensional discriminants.

This talk presents binning optimization for signal significance directly in multi-dimensional discriminants...

10. Awkward Arrays and JAX [10' + 5']

Ianna Osborne (Princeton University)

05/03/2026, 18:00

High-energy physics (HEP) relies on nested, variable-length (“ragged”) data structures that do not align naturally with the static, rectangular tensor abstractions assumed by most GPU compiler stacks. While Awkward Array provides a NumPy-like interface for such data, integrating it into the JAX ecosystem exposes an architectural mismatch between dynamic, offset-based structures and JAX’s...

11. Discussion

05/03/2026, 18:15

14. Differentiable Statistical Ecosystem with JAX [10' + 5']

Peter Fackeldey (Princeton University (US))

06/03/2026, 14:10

The propagation of gradients with backpropagation through a HEP analysis for end-to-end optimization begins at the last step of a physics analysis: the statistical measurement. Therefore, it is crucial to have statistical tools that are fully differentiable in order to calculate gradients with respect to the final physical measurement. This contribution provides an overview of how such fully...

15. Differentiable Programming in C++ and ROOT with Clad [25' + 5']

Jonas Rembser (CERN), Vassil Vasilev (Princeton University (US))

06/03/2026, 14:25

In this presentation, we make the case for differential programming in C++ for High Energy Physics. We will first introduce source code-transformation-based Automatic Differentiation (AD) with Clad, a Clang compiler plugin. Some success stories of how this is used for statistical analysis in ROOT are presented, including using Clad to differentiate through statistical likelihoods in RooFit and...

18. Discussion

06/03/2026, 14:55