2000 character limit reached
The NFLikelihood: an unsupervised DNNLikelihood from Normalizing Flows
Published 18 Sep 2023 in hep-ph, cs.LG, and hep-ex | (2309.09743v3)
Abstract: We propose the NFLikelihood, an unsupervised version, based on Normalizing Flows, of the DNNLikelihood proposed in Ref.[1]. We show, through realistic examples, how Autoregressive Flows, based on affine and rational quadratic spline bijectors, are able to learn complicated high-dimensional Likelihoods arising in High Energy Physics (HEP) analyses. We focus on a toy LHC analysis example already considered in the literature and on two Effective Field Theory fits of flavor and electroweak observables, whose samples have been obtained throught the HEPFit code. We discuss advantages and disadvantages of the unsupervised approach with respect to the supervised one and discuss possible interplays of the two.
- A. Coccaro, M. Pierini, L. Silvestrini and R. Torre, “The DNNLikelihood: enhancing likelihood distribution with Deep Learning”, Eur.Phys.J.C 80 (2020) 664, arXiv:1911.03305 [Semantic Scholar].
- K. Cranmer et al., “Publishing statistical models: Getting the most out of particle physics experiments”, SciPost Phys. 12 (2022) 037, arXiv:2109.04981 [Semantic Scholar].
- A. Coccaro, M. Letizia, H. Reyes-Gonzalez and R. Torre, “On the curse of dimensionality for Normalizing Flows”, arXiv:2302.12024 [Semantic Scholar].
- S. S. Gu, Z. Ghahramani and R. E. Turner, “Neural Adaptive Sequential Monte Carlo”, in Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama and R. Garnett, eds., vol. 28, Curran Associates, Inc., 2015, arXiv:1506.03338 [Semantic Scholar].
- B. Paige and F. Wood, “Inference Networks for Sequential Monte Carlo in Graphical Models”, in Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML’16, pp. 3040–3049, JMLR.org, 2016, arXiv:1602.06701 [Semantic Scholar].
- S. Foreman, T. Izubuchi, L. Jin, X.-Y. Jin, J. C. Osborn and A. Tomiya, “HMC with Normalizing Flows”, PoS LATTICE2021 (2022) 073, arXiv:2112.01586 [Semantic Scholar].
- D. C. Hackett, C.-C. Hsieh, M. S. Albergo, D. Boyda, J.-W. Chen, K.-F. Chen et al., “Flow-based sampling for multimodal distributions in lattice field theory”, arXiv:2107.00734 [Semantic Scholar].
- A. Singha, D. Chakrabarti and V. Arora, “Conditional normalizing flow for Markov chain Monte Carlo sampling in the critical region of lattice field theory”, Phys. Rev. D 107 (2023) 014512 [Semantic Scholar].
- M. Caselle, E. Cellini, A. Nada and M. Panero, “Stochastic normalizing flows for lattice field theory”, PoS LATTICE2022 (2023) 005, arXiv:2210.03139 [Semantic Scholar].
- A. G. D. G. Matthews, M. Arbel, D. J. Rezende and A. Doucet, “Continual Repeated Annealed Flow Transport Monte Carlo”, in International Conference on Machine Learning, 1, 2022, arXiv:2201.13117 [Semantic Scholar].
- K. Cranmer, G. Kanwar, S. Racanière, D. J. Rezende and P. Shanahan, “Advances in machine-learning-based sampling motivated by lattice quantum chromodynamics”, Nature Rev. Phys. 5 (2023) 526, arXiv:2309.01156 [Semantic Scholar].
- M. Feickert and B. Nachman, “A Living Review of Machine Learning for Particle Physics”, arXiv:2102.02770 [Semantic Scholar].
- A. Beck, M. Reboud and D. van Dyk, “Testable likelihoods for beyond-the-standard model fits”, Eur. Phys. J. C 83 (2023) 1115, arXiv:2309.10365.
- A. Buckley, M. Citron, S. Fichet, S. Kraml, W. Waltenberger and N. Wardle, “The Simplified Likelihood Framework”, JHEP 04 (2019) 064, arXiv:1809.05548 [Semantic Scholar].
- J. de Blas, M. Pierini, L. Reina and L. Silvestrini, “Impact of the recent measurements of the top-quark and W-boson masses on electroweak precision fits”, Phys. Rev. Lett. 129 (2022) 271801, arXiv:2204.04204 [Semantic Scholar].
- CMS Collaboration, “Measurement of the top quark mass using a profile likelihood approach with the lepton+jets final states in proton-proton collisions s=13TeV𝑠13normal-TeV\sqrt{s}=13~{}\mathrm{TeV}square-root start_ARG italic_s end_ARG = 13 roman_TeV”, arXiv:2302.01967 [Semantic Scholar].
- CDF Collaboration, T. Aaltonen et al., “High-precision measurement of the W boson mass with the CDF II detector”, Science 376 (2022) 170 [Semantic Scholar].
- J. De Blas et al., “HEPfit: a code for the combination of indirect and direct constraints on high energy physics models”, Eur. Phys. J. C 80 (2020) 456, arXiv:1910.14012 [Semantic Scholar].
- M. Ciuchini, A. M. Coutinho, M. Fedele, E. Franco, A. Paul, L. Silvestrini et al., “New Physics in b→sℓ+ℓ−normal-→𝑏𝑠superscriptnormal-ℓsuperscriptnormal-ℓb\to s\ell^{+}\ell^{-}italic_b → italic_s roman_ℓ start_POSTSUPERSCRIPT + end_POSTSUPERSCRIPT roman_ℓ start_POSTSUPERSCRIPT - end_POSTSUPERSCRIPT confronts new data on Lepton Universality”, Eur. Phys. J. C79 (2019) 719, arXiv:1903.09632 [Semantic Scholar].
- J. Rabin, G. Peyré, J. Delon and M. Bernot, “Wasserstein Barycenter and Its Application to Texture Mixing”, in Scale Space and Variational Methods in Computer Vision, A. M. Bruckstein, B. M. ter Haar Romeny, A. M. Bronstein and M. M. Bronstein, eds., pp. 435–446, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012 [Semantic Scholar].
- N. Bonneel, J. Rabin, G. Peyré and H. Pfister, “Sliced and Radon Wasserstein Barycenters of Measures”, Journal of Mathematical Imaging and Vision 51 (2015) 22 [Semantic Scholar].
- M. E. Muller, “A note on a method for generating points uniformly on n-dimensional spheres”, Commun. ACM 2 (1959) 19 [Semantic Scholar].
- G. Papamakarios, T. Pavlakou and I. Murray, “Masked Autoregressive Flow for Density Estimation”, in Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan et al., eds., vol. 30, Curran Associates, Inc., 2017, arXiv:1705.07057 [Semantic Scholar].
- C. Durkan, A. Bekasov, I. Murray and G. Papamakarios, “Neural Spline Flows”, in Proceedings of the 33rd International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA, 2019, arXiv:1906.04032 [Semantic Scholar].
- https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/SoftClip.
- Code repository for this paper on GitHub \faGithub.
- NF4HEP code repository on GitHub \faGithub.
- Data repository for this paper on Zenodo Zenodo.
- C. Winkler, D. Worrall, E. Hoogeboom and M. Welling, “Learning likelihoods with conditional normalizing flows”, arXiv:1912.00042 [Semantic Scholar].
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.