Sort by
Refine Your Search
-
suitable data models [CSC+23]. Objectives As far as the design of efficient numerical algorithms in an off-the-grid setting is concerned, the problem is challenging, since the optimization is defined in
-
, the post-doctoral fellow will consider designing distributed learning algorithms for streaming manifold-valued data. Experiments will be carried out on urban, coastal, and underwater DAS data. The novelty
-
. Processing this response provides estimates of the local variations in acoustic pressure along the fiber, over distances ranging from 40km up to 140km with some systems. This technique, called Distributed
-
learning community. Basically, once the observed data is identified with a probability distribution (possibly the empirical mass function), optimal transport allows to consistently assess the similarity
-
frameworks, as they impose minimal, if any, assumptions about the underlying data distribution, making them more effective for detecting a wide range of changes. The CPD algorithms will be designed
-
. The monitoring of telecommunications and energy production and distribution networks are characteristic examples of such time-critical applications. The project aims to propose unsupervised online CPD algorithms
-
, sensor failures, or the aggregation of datasets from multiple sources. There is a rich literature on how to impute missing values, for example, considering the EM algorithm [Dempster et al., 1977], low
-
We are looking for a postdoc to join the Interdisciplinary Institutes for Artificial Intelligence 3IA Cˆote d’Azur, in the beatiful French Riviera, to work with 3IA Chair Emanuele Natale on problems
-
heterogeneity, i.e., the fact that clients' local datasets are in general drawn from different distributions. Statistical heterogeneity for example slows down the convergence of FL algorithms [5]. In this thesis
-
modeling the dynamic of the data evolution is clearly important. The purpose of this postdoc position, within the Institut 3IA Côte d'Azur (Univ. Côte d’Azur & INRIA), will be focused on the development and