Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Hierarchical Neural Simulation-Based Inference Over Event Ensembles (2306.12584v2)

Published 21 Jun 2023 in stat.ML, astro-ph.IM, cs.LG, and hep-ex

Abstract: When analyzing real-world data it is common to work with event ensembles, which comprise sets of observations that collectively constrain the parameters of an underlying model of interest. Such models often have a hierarchical structure, where "local" parameters impact individual events and "global" parameters influence the entire dataset. We introduce practical approaches for frequentist and Bayesian dataset-wide probabilistic inference in cases where the likelihood is intractable, but simulations can be realized via a hierarchical forward model. We construct neural estimators for the likelihood(-ratio) or posterior and show that explicitly accounting for the model's hierarchical structure can lead to significantly tighter parameter constraints. We ground our discussion using case studies from the physical sciences, focusing on examples from particle physics and cosmology.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Amortized variational inference for simple hierarchical models. Advances in Neural Information Processing Systems, 34:21388–21399, 2021.
  2. Estimating the warm dark matter mass from strong lensing images with truncated marginal neural ratio estimation. Monthly Notices of the Royal Astronomical Society, 518(2):2746–2760, 2023.
  3. On the dynamics of inference and learning. arXiv preprint arXiv:2204.12939, 2022.
  4. JAX: composable transformations of Python+NumPy programs, 2018. URL http://github.com/google/jax.
  5. Mining for dark matter substructure: Inferring subhalo population properties from strong lenses with machine learning. The Astrophysical Journal, 886(1):49, 2019.
  6. Particle flow Bayes’ rule. In International Conference on Machine Learning, pp. 1022–1031. PMLR, 2019.
  7. One never walks alone: the effect of the perturber population on subhalo measurements in strong gravitational lenses. arXiv preprint arXiv:2209.09918, 2022.
  8. Approximating likelihood ratios with calibrated discriminative classifiers. arXiv preprint arXiv:1506.02169, 2015.
  9. The frontier of simulation-based inference. Proceedings of the National Academy of Sciences, 117(48):30055–30062, 2020.
  10. nflows: normalizing flows in PyTorch, November 2020. URL https://doi.org/10.5281/zenodo.4296287.
  11. William Falcon et al. Pytorchlightning/pytorch-lightning: 0.7.6 release, May 2020. URL https://doi.org/10.5281/zenodo.3828935.
  12. Score modeling for simulation-based inference. arXiv preprint arXiv:2209.14249, 2022.
  13. Charles R. Harris et al. Array programming with NumPy. Nature, 585(7825):357–362, September 2020. doi: 10.1038/s41586-020-2649-2. URL https://doi.org/10.1038/s41586-020-2649-2.
  14. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  15. Lukas Heinrich. Learning optimal test statistics in the presence of nuisance parameters. arXiv preprint arXiv:2203.13079, 2022.
  16. A trust crisis in simulation-based inference? your posterior approximations can be unfaithful. arXiv preprint arXiv:2110.06581, 2021.
  17. J. D. Hunter. Matplotlib: A 2d graphics environment. Computing In Science & Engineering, 9(3):90–95, 2007.
  18. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  19. Thomas Kluyver et al. Jupyter notebooks - a publishing format for reproducible computational workflows. In ELPUB, 2016.
  20. Decoupled weight decay regularization. In International Conference on Learning Representations, 2019.
  21. Contrastive neural ratio estimation. Advances in Neural Information Processing Systems, 35:3262–3278, 2022.
  22. Detection is truncation: studying source populations with truncated marginal neural ratio estimation. arXiv preprint arXiv:2211.04291, 2022.
  23. Learning from many collider events at once. Physical Review D, 103(11):116013, 2021.
  24. J Neyman and Pearson ES. On the problem of the most efficient tests of statistical hypotheses. Philosophical Transactions of the Royal Society of London. Series A, Containing Papers of a Mathematical or Physical Character231:289–337, 1933.
  25. Fast ε𝜀\varepsilonitalic_ε-free inference of simulation models with bayesian conditional density estimation. Advances in neural information processing systems, 29, 2016.
  26. Masked autoregressive flow for density estimation. Advances in neural information processing systems, 30, 2017.
  27. Adam Paszke et al. Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett (eds.), Advances in Neural Information Processing Systems 32, pp.  8024–8035. Curran Associates, Inc., 2019. URL http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf.
  28. Formal algorithms for transformers. arXiv preprint arXiv:2207.09238, 2022.
  29. Variational inference with normalizing flows. In International conference on machine learning, pp. 1530–1538. PMLR, 2015.
  30. HNPE: Leveraging global parameters for neural posterior estimation. Advances in Neural Information Processing Systems, 34:13432–13443, 2021.
  31. Alex Rogozhnikov. Einops: Clear and reliable tensor manipulations with einstein-like notation. In International Conference on Learning Representations, 2022. URL https://openreview.net/forum?id=oapKSVM2bcj.
  32. Probabilistic programming in Python using PyMC3. PeerJ Computer Science 2:e55, 2016.
  33. The ATLAS Collaboration. A detailed map of Higgs boson interactions by the ATLAS experiment ten years after the discovery. Nature 607, 52–59, 2022.
  34. The CMS Collaboration. A portrait of the Higgs boson by the CMS experiment ten years after the discovery. Nature 607, 60–68, 2022.
  35. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  36. Pauli Virtanen et al. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nature Methods, 2020. doi: https://doi.org/10.1038/s41592-019-0686-2.
  37. Hierarchical inference with bayesian neural networks: An application to strong gravitational lensing. The Astrophysical Journal, 909(2):187, 2021.
  38. From images to dark matter: End-to-end inference of substructure from hundreds of strong gravitational lenses. arXiv preprint arXiv:2203.00690, 2022.
  39. Deep sets. Advances in neural information processing systems, 30, 2017.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now