Lorenzo Pacchiardi

selected publications and preprints

1. arXiv

   Generalized Bayesian Likelihood-Free Inference Using Scoring Rules Estimators

   Pacchiardi, Lorenzo, and Dutta, Ritabrata

   arXiv preprint arXiv:2104.03889 2021

   Abs Bib HTML Code

   We propose a framework for Bayesian Likelihood-Free Inference (LFI) based on Generalized Bayesian Inference using scoring rules (SR). SR are used to evaluate probabilistic models given an observation; a proper SR is minimised in expectation when the model corresponds to the true data generating process for the observation. Using a strictly proper SR, for which the above minimum is unique, ensures posterior consistency of our method. As the likelihood function is intractable for LFI, we employ consistent estimators of SR using model simulations in a pseudo-marginal MCMC; we show the target of such chain converges to the exact SR posterior with increasing number of simulations. Furthermore, we note popular LFI techniques like Bayesian Synthetic Likelihood (BSL) and semiparametric BSL can be seen as special cases of our framework using only proper (but not strictly so) SR. We provide empirical results validating our consistency result and show how related approaches do not enjoy this property. Practically, we use the Energy and Kernel Scores, but our general framework sets the stage for extensions with other scoring rules.

   @article{pacchiardi2021generalized,
     abbr = {arXiv},
     bibtex_show = {true},
     title = {Generalized Bayesian Likelihood-Free Inference Using Scoring Rules Estimators},
     author = {Pacchiardi, Lorenzo and Dutta, Ritabrata},
     journal = {arXiv preprint arXiv:2104.03889},
     year = {2021},
     eprint = {2104.03889},
     archiveprefix = {arXiv},
     html = {https://arxiv.org/abs/2104.03889},
     primaryclass = {stat.ME},
     code = {https://github.com/LoryPack/GenBayes_LikelihoodFree_ScoringRules},
     selected = {true}
   }

2. arXiv

   Score Matched Conditional Exponential Families for Likelihood-Free Inference

   Pacchiardi, Lorenzo, and Dutta, Ritabrata

   arXiv preprint arXiv:2012.10903 2020

   Abs Bib HTML Code

   To perform Bayesian inference for stochastic simulator models for which the likelihood is not accessible, Likelihood-Free Inference (LFI) relies on simulations from the model. Standard LFI methods can be split according to how these simulations are used: to build an explicit Surrogate Likelihood, or to accept/reject parameter values according to a measure of distance from the observations (Approximate Bayesian Computation (ABC)). In both cases, simulations are adaptively tailored to the value of the observation. Here, we generate parameter-simulation pairs from the model independently on the observation, and use them to learn a conditional exponential family likelihood approximation; to parametrize it, we use Neural Networks whose weights are tuned with Score Matching. With our likelihood approximation, we can employ MCMC for doubly intractable distributions to draw samples from the posterior for any number of observations without additional model simulations, with performance competitive to comparable approaches. Further, the sufficient statistics of the exponential family can be used as summaries in ABC, outperforming the state-of-the-art method in five different models with known likelihood. Finally, we apply our method to a challenging model from meteorology.

   @article{pacchiardi2020score,
     abbr = {arXiv},
     bibtex_show = {true},
     title = {Score Matched Conditional Exponential Families for Likelihood-Free Inference},
     author = {Pacchiardi, Lorenzo and Dutta, Ritabrata},
     journal = {arXiv preprint arXiv:2012.10903},
     year = {2020},
     html = {https://arxiv.org/abs/2012.10903},
     code = {http://github.com/LoryPack/SM-ExpFam-LFI},
     selected = {true}
   }

3. arXiv

   ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation

   Dutta, Ritabrata, Schoengens, Marcel, Pacchiardi, Lorenzo, Ummadisingu, Avinash, Widmer, Nicole, Onnela, Jukka-Pekka, and Mira, Antonietta

   arXiv preprint arXiv:1711.04694 2020

   Abs Bib HTML Code

   ABCpy is a highly modular scientific library for Approximate Bayesian Computation (ABC) written in Python. The main contribution of this paper is to document a software engineering effort that enables domain scientists to easily apply ABC to their research without being ABC experts; using ABCpy they can easily run large parallel simulations without much knowledge about parallelization. Further, ABCpy enables ABC experts to easily develop new inference schemes and evaluate them in a standardized environment and to extend the library with new algorithms. These benefits come mainly from the modularity of ABCpy. We give an overview of the design of ABCpy and provide a performance evaluation concentrating on parallelization. This points us towards the inherent imbalance in some of the ABC algorithms. We develop a dynamic scheduling MPI implementation to mitigate this issue and evaluate the various ABC algorithms according to their adaptability towards high-performance computing.

   @article{dutta2017abcpy,
     abbr = {arXiv},
     bibtex_show = {true},
     title = {ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation},
     author = {Dutta, Ritabrata and Schoengens, Marcel and Pacchiardi, Lorenzo and Ummadisingu, Avinash and Widmer, Nicole and Onnela, Jukka-Pekka and Mira, Antonietta},
     journal = {arXiv preprint arXiv:1711.04694},
     html = {https://arxiv.org/abs/1711.04694},
     year = {2020},
     code = {https://github.com/eth-cscs/abcpy},
     selected = {true}
   }