On the afternoon of September 22nd and 23rd, the "HUST-UPSaclay Workshop on Mathematics for Data Science" was held online. Prof. Pascal, Prof. Sheng Yang, Prof. Gramfort, Researcher Chazal, Researcher Chouzenoux, Researcher Mazanti, and Researcher Pfeiffer, all of whom are from UPSaclay, and Associate Prof. Gao Ting from HUST delivered speeches on recent advancements in “Mathematical for Data Science”.
The two half-day workshop was streamed on Zoom and AI TIME, attracting more than 40,000 viewers.
The workshop on September 22nd was hosted by Zhenyu Liao from the School of Electronic Information and Communications (EIC) of HUST. First, Prof. Qiu Caiming, the Dean of EIC, delivered an opening speech. He extended his warm welcome to the experts from UPSaclay and looked forward to deeper academic exchanges and cooperation between the two universities in the field of "Mathematics + Information".
Next, Prof. Pascal gave a presentation on " Robust statistics and clustering - Application to signal and image processing", in which he studied the unsupervised clustering problem in machine learning and proposed a novel and flexible F-EM algorithm for elliptically symmetric distribution families of data. Furthermore, he proved some statistical theoretical properties of the algorithm and further demonstrated its good performance through numerical experiments. Also, the algorithm was applied to PoLSAR image processing problems.
Prof. Sheng Yang made a speech on “Context-Tree-Based Lossy Compression". He proposed an effective lossy variable compression scheme and designed a quantized compander to achieve Uniform quantization by introducing a nonlinear transformation and creating low-loss index series compression based on context-tree.
Gramfort delivered a presentation on "Learning without labels on multivariate bio-signals: From unsupervised to self-supervised learning". He proposed using both unsupervised and self-supervised learning to examine label-free multivariate bio-signals. He also explored the evolution from unsupervised to supervised learning, and then presented the applications of the proposed methods.
Ting Gao from HUST gave a presentation on "Identifying, prediction, and control in non-Gaussian stochastic dynamical systems", in which she comprehensively discussed the application of SDEs in machine learning from three aspects: learning the system identifiability for SDEs with Levy noise, discovering the transition phenomenon from data, and predicting with complex datasets by SDEs.
The workshop on September 23rd was chaired by Prof. Yacine Chitour who works at the L2S Laboratory of UPSaclay.
Chazal made a presentation themed on "Topological Data Analysis to improve learning models: an introduction and a few examples". In his work on machine learning and artificial intelligence, he discussed the robustness and interpretability of a tangible and effective TDA approach, which is well-grounded in mathematics. He further noted that the approach can be effectively combined with other machine learning and artificial intelligence techniques.
Chouzenoux delivered a speech on "Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution". She proposed a novel blind image deconvolution Based on the variational Bayesian algorithm and the deep neural network architecture, and the corresponding estimation of which is accurate in both image and the blur kernels. The approach is also competitive in computational efficiency.
Mazanti gave a presentation themed on "Modelling crowd behavior through mean field games". He introduced some recent theoretical advances in crowd movement through mean field games. In contrast to other work, this macroscopic model considers the strategic decisions of pedestrians and predicts the behavior of other pedestrians based on their experience, which can be used to choose their trajectories. Particularly, in this report, he demonstrated the existence of steady states for this kind of mean-field game and described them using a system of partial differential equations.
Pfeiffer delivered a presentation on "Conditional gradient method for mean-field type problems". He proposed an effective generalized conditional gradient algorithm for potential mean-field games. Also, this approach can be interpreted as a learning method called fictitious play.
Written by: Liao Zhenyu, Zhang Jiani
Edited by: Peng Yumeng
Chinese
