High-fidelity simulators that connect theoretical models with observations are indispensable tools in many sciences. If the likelihood is known, inference can proceed using standard techniques. However, when the likelihood is intractable or unknown, a simulator makes it possible to infer the parameters of a theoretical model directly from real and simulated observations when coupled with machine learning. We introduce an extension of the recently proposed likelihood-free frequentist inference ( Code to reproduce all of our results is available on
- Award ID(s):
- 1836650
- PAR ID:
- 10256982
- Editor(s):
- Doglioni, C.; Kim, D.; Stewart, G.A.; Silvestris, L.; Jackson, P.; Kamleh, W.
- Date Published:
- Journal Name:
- EPJ Web of Conferences
- Volume:
- 245
- ISSN:
- 2100-014X
- Page Range / eLocation ID:
- 06026
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract LF2I ) approach that makes it possible to construct confidence sets with thep -value function and to use the same function to check the coverage explicitly at any given parameter point. LikeLF2I , this extension yields provably valid confidence sets in parameter inference problems for which a high-fidelity simulator is available. The utility of our algorithm is illustrated by applying it to three pedagogically interesting examples: the first is from cosmology, the second from high-energy physics and astronomy, both with tractable likelihoods, while the third, with an intractable likelihood, is from epidemiology3https://github.com/AliAlkadhim/ALFFI . -
more » « less
Abstract Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are often computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare, and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among 5 locations and found they achieve close to the same levels of accuracy as Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also implemented a method of uncertainty quantification called conformalized quantile regression that we demonstrate has similar patterns of sensitivity to model misspecification as Bayesian highest posterior density (HPD) and greatly overlap with HPDs, but have lower precision (more conservative). Finally, we trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of region-specific epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster after training. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models.
-
Abernethy, Jacob ; Agarwal, Shivani (Ed.)We study a variant of the sparse PCA (principal component analysis) problem in the “hard” regime, where the inference task is possible yet no polynomial-time algorithm is known to exist. Prior work, based on the low-degree likelihood ratio, has conjectured a precise expression for the best possible (sub-exponential) runtime throughout the hard regime. Following instead a statistical physics inspired point of view, we show bounds on the depth of free energy wells for various Gibbs measures naturally associated to the problem. These free energy wells imply hitting time lower bounds that corroborate the low-degree conjecture: we show that a class of natural MCMC (Markov chain Monte Carlo) methods (with worst-case initialization) cannot solve sparse PCA with less than the conjectured runtime. These lower bounds apply to a wide range of values for two tuning parameters: temperature and sparsity misparametrization. Finally, we prove that the Overlap Gap Property (OGP), a structural property that implies failure of certain local search algorithms, holds in a significant part of the hard regime.more » « less
-
Nonlinear state-space models are ubiquitous in modeling real-world dynamical systems. Sequential Monte Carlo (SMC) techniques, also known as particle methods, are a well-known class of parameter estimation methods for this general class of state-space models. Existing SMC-based techniques rely on excessive sampling of the parameter space, which makes their computation intractable for large systems or tall data sets. Bayesian optimization techniques have been used for fast inference in state-space models with intractable likelihoods. These techniques aim to find the maximum of the likelihood function by sequential sampling of the parameter space through a single SMC approximator. Various SMC approximators with different fidelities and computational costs are often available for sample- based likelihood approximation. In this paper, we propose a multi-fidelity Bayesian optimization algorithm for the inference of general nonlinear state-space models (MFBO-SSM), which enables simultaneous sequential selection of parameters and approximators. The accuracy and speed of the algorithm are demonstrated by numerical experiments using synthetic gene expression data from a gene regulatory network model and real data from the VIX stock price index.more » « less
-
Abstract The production of heavy neutral mass resonances, $$\text {Z}^{\prime }$$ Z ′ , has been widely studied theoretically and experimentally. Although the nature, mass, couplings, and associated quantum numbers of this hypothetical particle are yet to be determined, current LHC experimental results have set strong constraints assuming the simplest beyond Standard Model (SM) hypotheses. We present a new feasibility study on the production of a $$\text {Z}^{\prime }$$ Z ′ boson at the LHC, with family non-universal couplings, considering proton–proton collisions at $$\sqrt{s} = 13$$ s = 13 and 14 TeV. Such a hypothesis is well motivated theoretically and it can explain observed differences between SM predictions and experimental results, as well as being a useful tool to further probe recent results in searches for new physics considering non-universal fermion couplings. We work under two simplified phenomenological frameworks where the $$\textrm{Z}^{\prime }$$ Z ′ masses and couplings to the SM particles are free parameters, and consider final states of the $$\text {Z}^{\prime }$$ Z ′ decaying to a pair of $$\textrm{b}$$ b quarks. The analysis is performed using machine learning techniques to maximize the sensitivity. Despite being a well motivated physics case in its own merit, such scenarios have not been fully considered in ongoing searches at the LHC. We note the proposed search methodology can be a key mode for discovery over a large mass range, including low masses, traditionally considered difficult due to experimental constrains. In addition, the proposed search is complementary to existing strategies.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1051/epjconf/202024506026
