Archive for Université Paris Dauphine
Pr[AI]rie Scientific Workshop 2024
Posted in Statistics, Travel, University life with tags 3IA, AI, French Institutes of Artificial Intelligence, French Ministry of Higher Education Research and Innovation, Institut PR[AI]RIE, Instituts Interdisciplinaires d’Intelligence Artificielle, Paris, PaRis AI Research InstitutE, PSL Research University, The Prairie Chair, Université Paris Dauphine, workshp[ on March 22, 2024 by xi'anpostdoctoral research positions at PariSanté
Posted in pictures, Statistics, Travel, University life with tags #ERCSyG, ABC, Bayesian decision theory, data privacy, ERC, ERC Synergy Grant, European Research Council, federated learning, French universities, game theory, MCMC, multi-agent decision theory, Ocean, Paris, PariSanté campus, postdoctoral position, recommendation, Université Paris Dauphine, University of California Berkeley, University of Warwick on March 7, 2024 by xi'anThanks to the 2023-2029 ERC Synergy grant OCEAN (On intelligenCE And Networks: Synergistic research in Bayesian Statistics, Microeconomics and Computer Sciences), I am seeking one or two postdoctoral researchers with an interest in Bayesian federated learning, distributed MCMC, approximate Bayesian inference and computing, and data privacy.
The project is based at Université Paris Dauphine, on the new PariSanté Campus. The postdocs will join the OCEAN teams of researchers directed by Éric Moulines and myself (Christian P Robert) to work on the above themes with multiple possibilities of focus from statistical theory, to Bayesian methodology, to decision theory, to algorithms, to medical applications. Collaborations with the OCEAN teams of researchers directed by Michael Jordan (Berkeley) and Gareth Roberts (Warwick) will further be encouraged and related travel will be supported.
Qualifications
The candidates should hold a doctorate in applied maths, statistics or machine learning, with demonstrated skills in Bayesian analysis, game theory, Monte Carlo methodology or numerical probability, an excellent record of publications in these domains, and an interest in working as part of an interdisciplinary international team. Scientific maturity and research autonomy are a must for applying. There is no deadline for the positions, which will be filled when a suitable candidate is selected.
Funding
Besides a 2 year postdoctoral contract at Université Paris Dauphine (with possible extension for another year), at a salary of 31K€ per year, the project will fund travel to OCEAN partners’ institutions (University of Warwick or University of Berkeley) and participation to yearly summer schools and conferences. Standard French university benefits are attached to the position and no teaching duty is involved, as per ERC rules.
The starting date of the postdoctoral positions is negotiable depending on the applicants’ availability.
Application Procedure
- To apply, please send the following entries in one pdf file to Christian Robert (bayesianstatistics@gmail.com).
- a letter of application,
- a CV,
Letters of recommendation are to be sent directly by their author.
insufficient Gibbs at One World ABC [25/01]
Posted in Kids, pictures, Statistics, Travel, University life with tags ABC, Approximate Bayesian computation, CEREMADE, GMT, inefficient statistics, insufficiency, latent variable, mad, median, One World ABC Seminar, PariSanté campus, Université Paris Dauphine, webinar on January 22, 2024 by xi'anThe next [on-line] One World Approximate Bayesian Computation (ABC) Seminar will be delivered by Antoine Luciano, currently writing his PhD with Robin Ryder and I. It will take place at 9am, UK/GMT time, on Thursday 25 January, with members of the stats lab here in CEREMADE attending Antoine’s lecture live at the PariSanté campus. Here is the abstract for the talk:
In some applied scenarios, the availability of complete data is restricted, often due to privacy concerns, and only aggregated, robust and inefficient statistics derived from the data are accessible. These robust statistics are not sufficient, but they demonstrate reduced sensitivity to outliers and offer enhanced data protection due to their higher breakdown point. In this article, operating within a parametric framework, we propose a method to sample from the posterior distribution of parameters conditioned on different robust and inefficient statistics: specifically, the pairs (median, MAD) or (median, IQR), or one or more quantiles. Leveraging a Gibbs sampler and the simulation of latent augmented data, our approach facilitates simulation according to the posterior distribution of parameters belonging to specific families of distributions. We demonstrate its applicability on the Gaussian, Cauchy, and translated Weibull families.
based on our recent arXival.