Research Seminar - Charles Bouveyron
We are pleased to announce the upcoming Research Seminar on November 11, 2022.
The Institute for Statistics and Mathematics is pleased to invite you to the next research seminar, taking place on campus:
Charles Bouveyron (Equipe Maasai, INRIA Sophia-Antipolis; Institut 3IA Côte d'Azur, Université Côte d’Azur)
Statistical Learning With Interaction Data: Applications
Friday, November 11, 2022, 10:30 am, Building TC, Room TC.3.01
In this talk, we will focus on the problem of statistical learning with interaction data. This work is motivated by two real-world applications: the modeling and clustering of social networks, on the one hand, and of Pharmacovigilance data, on the other hand. To this end, we developed two model-based approaches. First, we propose the deep latent position model (DeepLPM), an end-to-end generative clustering approach which combines the widely used latent position model (LPM) for network analysis with a graph convolutional network (GCN) encoding strategy. An original estimation algorithm is introduced to integrate the explicit optimization of the posterior clustering probabilities via variational inference and the implicit optimization using stochastic gradient descent for graph reconstruction. Second, for the Pharmacovigilance problem, we introduce a latent block model for the dynamic co-clustering of count data streams with high sparsity. We assume that the observations follow a time and block dependent mixture of zero-inflated Poisson distributions, which combines two independent processes: a dynamic mixture of Poisson distributions and a time-dependent sparsity process. To model and detect abrupt changes in the dynamics of both clusters memberships and data sparsity, the mixing and sparsity proportions are modeled through systems of ordinary differential equations. The model inference relies on an original variational procedure whose maximization step trains recurrent neural networks in order to solve the dynamical systems. Numerical experiments on simulated data sets demonstrate the effectiveness of the proposed methodologies for the two problems.
We aim to stream all on-campus talks via Zoom. A direct link to the stream will be posted on our website.
For further information and the seminar schedule, please see: