Statistical learning from high-dimensional and distributed data

When

01/10/2025    
2:00 pm-3:00 pm
Faicel Chamroukhi
SystemX

Where

Zoom + Amphi 4 chez Télécom-Paris
19 Place Marguerite Perey, Palaiseau, 91120

Event Type

Modern learning algorithms must tackle real-world problems involving complex, heterogeneous, often unlabeled, high-dimensional, and potentially large-scale and/or distributed data.

In this talk, the speaker will present a statistical learning approach focused on the design of latent variable models, with approximation capabilities and learning guarantees. He will begin by introducing mixture-of-experts models designed for heterogeneous data and high-dimensional functional predictors, which may be noisy, and their training via regularization methods, enabling sparse and interpretable representations.

Finally, when data are inherently distributed and/or constrained by confidentiality requirements, the speaker will present federated learning and aggregation strategy for (statistical or neural) models trained in parallel.