collaborators

6 papers

cs.LG2026

Diffusion enabled Optimal Transport distances for graph matching

Iman Seyedi, Francesco Archetti

This paper introduces Diffusion Semi-Relaxed Fused Gromov-Wasserstein (DsrFGW), a novel method for graph comparison that unifies node features and structural connectivity through o…

math.OC2026

Wasserstein-enabled characterization of designs and myopic decisions in Bayesian Optimization

Antonio Candelieri, Francesco Archetti

Impractical assumptions, an inherently myopic nature, and the crucial role of the initial design, all together contribute to making theoretical convergence proofs of little value i…

cs.LG2026

Weighted Wasserstein Barycenter of Gaussian Processes for exotic Bayesian Optimization tasks

Antonio Candelieri, Francesco Archetti

Exploiting the analogy between Gaussian Distributions and Gaussian Processes' posterior, we present how the weighted Wasserstein Barycenter of Gaussian Processes (W2BGP) can be use…

physics.soc-ph2025

Structural Vulnerability Assessment in Urban Transport Networks: A Network-Wide Geometric Approach Using Gromov-Wasserstein

Iman Seyedi, Antonio Candelieri, Enza Messina +1

Urban transportation networks are inherently vulnerable to disruptions that affect connectivity and passenger mobility. Traditional graph_theoretic metrics, such as betweenness and…

math.OC2025

Gromov-Wasserstein and optimal transport: from assignment problems to probabilistic numeric

Iman Seyedi, Antonio Candelieri, Enza Messina +1

The assignment problem, a cornerstone of operations research, seeks an optimal one-to-one mapping between agents and tasks to minimize total cost. This work traces its evolution fr…

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…