activity
20202024
most citedA PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing stat.MLShow all

2 papers · 1 filter

stat.ML2024

Closed-form Filtering for Non-linear Systems

Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj +1

Sequential Bayesian Filtering aims to estimate the current state distribution of a Hidden Markov Model, given the past observations. The problem is well-known to be intractable for…

stat.ML2022

Measuring dissimilarity with diffeomorphism invariance

Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj +1

Measures of similarity (or dissimilarity) are a key ingredient to many machine learning algorithms. We introduce DID, a pairwise dissimilarity measure applicable to a wide range of…