Portrait de Abdessamad EL KABID n'est pas disponible

Abdessamad EL KABID

Collaborateur·rice alumni - UdeM
Superviseur⋅e principal⋅e
Yoshua Bengio
Co-supervisor
Loubna Benabbou
Sujets de recherche
Apprentissage profond
IA pour les équations aux dérivées partielles (EDP)
Théorie de l'apprentissage automatique

Publications

Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
Oliver Ethan Richardson
Abdessamad EL KABID
Mandana Samiei
Mehran Shakerinava
Joseph D Viviano
Ali Parviz
Yoshua Bengio
We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a sub… (voir plus)set of the model and resolve inconsistencies using the parameters under control. This framework, which we call Local Inconsistency Resolution (LIR) is built upon Probabilistic Dependency Graphs (PDGs), which provide a flexible representational foundation capable of capturing inconsistent beliefs. We show how LIR unifies and generalizes a wide variety of important algorithms in the literature, including the Expectation-Maximization (EM) algorithm, belief propagation, adversarial training, GANs, and GFlowNets. Each of these methods can be recovered as a specific instance of LIR by choosing a procedure to direct focus (attention and control). We implement this algorithm for discrete PDGs and study its properties on synthetically generated PDGs, comparing its behavior to the global optimization semantics of the full PDG.
2026-02-02
International Conference on Artificial Intelligence and Statistics (spotlight)
openreview.net
openreview.net