mlsanityData to 7 Oct 2026

Branches of a Tree: Taking Derivatives of Programs with Discrete and Branching Randomness in High Energy Physics

arXiv 2308.16680 ↗First posted 31 Aug 2023stat.ML cs.LG hep-excited by 6

Not on the map. Why?

Abstract (arXiv)

We propose to apply several gradient estimation techniques to enable the differentiation of programs with discrete randomness in High Energy Physics. Such programs are common in High Energy Physics due to the presence of branching processes and clustering-based analysis. Thus differentiating such programs can open the way for gradient based optimization in the context of detector design optimization, simulator tuning, or data analysis and reconstruction optimization. We discuss several possible gradient estimation strategies, including the recent Stochastic AD method, and compare them in simplified detector design experiments. In doing so we develop, to the best of our knowledge, the first fully differentiable branching program.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 31 Aug 2023.

Builds on

18 of 41 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Automatic differentiation in machine learning: a surveycited by 846
  4. 2019The frontier of simulation-based inferencecited by 490
  5. 2019Monte Carlo Gradient Estimation in Machine Learningcited by 281
  6. 2015Gradient Estimation Using Stochastic Computation Graphscited by 120
  7. 2022Automatic Differentiation of Programs with Discrete Randomnesscited by 28
  8. 2022New directions for surrogate models and differentiable programming for High Energy Physics detector simulationcited by 16
  9. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  10. 2021Storchastic: A Framework for General Stochastic Automatic Differentiationcited by 11
  11. 2022ADEV: Sound Automatic Differentiation of Expected Values of Probabilistic Programscited by 11
  12. 2022neos: End-to-End-Optimised Summary Statistics for High Energy Physicscited by 10
6 more
  1. 2022Differentiable Matrix Elements with MadJaxcited by 8
  2. 2020PDFFlow: parton distribution functions on GPUcited by 5
  3. 2020Hierarchical clustering in particle physics through reinforcement learningcited by 5
  4. 2023Differentiating Metropolis-Hastings to Optimize Intractable Densitiescited by 5
  5. 2019Jet grooming through reinforcement learningcited by 3
  6. 2022Novel Light Field Imaging Device with Enhanced Light Collection for Cold Atom Cloudscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  2. 2024Finetuning Foundation Models for Joint Analysis Optimizationcited by 18
  3. 2024Generalizing Stochastic Smoothing for Differentiation and Gradient Estimationcited by 4
  4. 2023Differentiable Vertex Fitting for Jet Flavour Taggingcited by 3
  5. 2025End-to-End Optimal Detector Design with Mutual Information Surrogatescited by 2
  6. 2026Gradient estimators for parameter inference in discrete stochastic kinetic modelscited by 1