Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Transformers for Tabular Data: A Training Perspective of Self-Attention via Optimal Transport
Alessandro Quadrio, Antonio Candelieri
This thesis examines self-attention training through the lens of Optimal Transport (OT) and develops an OT-based alternative for tabular classification. The study tracks intermedia…
stat.ML2025
Wasserstein Barycenter Gaussian Process based Bayesian Optimization
Antonio Candelieri, Andrea Ponti, Francesco Archetti
Gaussian Process based Bayesian Optimization is a widely applied algorithm to learn and optimize under uncertainty, well-known for its sample efficiency. However, recently -- and m…