Dear all,
the next OWABI seminar www.warwick.ac.uk/oneworldabchttp://www.warwick.ac.uk/oneworldabc is quickly approaching, being scheduled on Thursday the 27th March at 11am UK time.
Our next speaker is Meïli Baragattihttps://www.vinifera-euromaster.eu/team/meili-baragatti/ (Université de Montpellier), who will talk about "Approximate Bayesian Computation with Deep Learning and Conformal Prediction", with an abstract reported below.
Abstract: Approximate Bayesian Computation (ABC) methods are commonly used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Classical ABC methods are based on nearest neighbor type algorithms and rely on the choice of so-called summary statistics, distances between datasets and a tolerance threshold. Recently, methods combining ABC with more complex machine learning algorithms have been proposed to mitigate the impact of these "user-choices''. In this talk, I will present you the first, to our knowledge, ABC method completely free of summary statistics, distance, and tolerance threshold. Moreover, in contrast with usual generalizations of the ABC method, it associates a confidence interval (having a proper frequentist marginal coverage) with the posterior mean estimation (or other moment-type estimates). This method, named ABCD-Conformal, uses a neural network with Monte Carlo Dropout to provide an estimation of the posterior mean (or other moment type functionals), and conformal theory to obtain associated confidence sets. I will compare its performances with other ABC methods on several examples, and show you that it is efficient for estimating multidimensional parameters, while being "amortized". Keywords: Likelihood-free inference · Approximate Bayesian computation · Convolutional neural networks · Dropout · Conformal prediction
Reference: M. Baragatti, B. Cloez, D. M´etivier, I. Sanchez. Approximate bayesian computation with deep learning and conformal prediction. Preprint at ArXiv: 2406.04874, 2024. This talk is hosted on the OWABI Ms Teams Channel, which is available here https://teams.microsoft.com/l/team/19%3AdhZ_4e_XLNJzCXPAMzTvT6BZ5KShEETkd_wt.... The MS Teams link to join Meïli Baragatti's talk is https://teams.microsoft.com/l/meetup-join/19%3adhZ_4e_XLNJzCXPAMzTvT6BZ5KShE... Meeting ID: 328 977 159 098 Passcode: zy9vS32A We're looking forward to seeing you at the next OWABI seminar, best, Massimiliano on the behalf of the OWABI Organisers
------ Dr. Massimiliano Tamborrino Reader (Associate Professor) and WIHEA Fellow Department of Statistics University of Warwick https://warwick.ac.uk/tamborrino
Dear all,
a reminder that the next OWABI seminar www.warwick.ac.uk/owabihttp://www.warwick.ac.uk/owabiis scheduled on Thursday the 27th March at 11am Uk time, when Meïli Baragattihttps://www.vinifera-euromaster.eu/team/meili-baragatti/ (Université de Montpellier) will talk about "Approximate Bayesian Computation with Deep Learning and Conformal Prediction", with an abstract reported below.
Abstract: Approximate Bayesian Computation (ABC) methods are commonly used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Classical ABC methods are based on nearest neighbor type algorithms and rely on the choice of so-called summary statistics, distances between datasets and a tolerance threshold. Recently, methods combining ABC with more complex machine learning algorithms have been proposed to mitigate the impact of these "user-choices''. In this talk, I will present you the first, to our knowledge, ABC method completely free of summary statistics, distance, and tolerance threshold. Moreover, in contrast with usual generalizations of the ABC method, it associates a confidence interval (having a proper frequentist marginal coverage) with the posterior mean estimation (or other moment-type estimates). This method, named ABCD-Conformal, uses a neural network with Monte Carlo Dropout to provide an estimation of the posterior mean (or other moment type functionals), and conformal theory to obtain associated confidence sets. I will compare its performances with other ABC methods on several examples, and show you that it is efficient for estimating multidimensional parameters, while being "amortized". Keywords: Likelihood-free inference · Approximate Bayesian computation · Convolutional neural networks · Dropout · Conformal prediction
Reference: M. Baragatti, B. Cloez, D. M´etivier, I. Sanchez. Approximate bayesian computation with deep learning and conformal prediction. Preprint at ArXiv: 2406.04874, 2024. This talk is hosted on the OWABI Ms Teams Channel, which is available here https://teams.microsoft.com/l/team/19%3AdhZ_4e_XLNJzCXPAMzTvT6BZ5KShEETkd_wt.... The MS Teams link to join Meïli Baragatti's talk is https://teams.microsoft.com/l/meetup-join/19%3adhZ_4e_XLNJzCXPAMzTvT6BZ5KShE... Meeting ID: 328 977 159 098 Passcode: zy9vS32A We're looking forward to seeing you on Thursday, best, Massimiliano on the behalf of the OWABI Organisers
------ Dr. Massimiliano Tamborrino Reader (Associate Professor) and WIHEA Fellow Department of Statistics University of Warwick https://warwick.ac.uk/tamborrino