3 papers
cs.LG2025
Relative Representations: Topological and Geometric Perspectives
Alejandro GarcÃa-Castellanos, Giovanni Luca Marchetti, Danica Kragic +1
Relative representations are an established approach to zero-shot model stitching, consisting of a non-trainable transformation of the latent space of a deep neural network. Based…
math.AG2025
Testing the variety hypothesis
A. Lerario, P. Roos Hoefgeest, M. Scolamiero +1
Given a probability measure on the unit disk, we study the problem of deciding whether, for some threshold probability, this measure is supported near a real algebraic variety of g…
stat.ML2025
Certifying Robustness via Topological Representations
Jens Agerberg, Andrea Guidolin, Andrea Martinelli +3
We propose a neural network architecture that can learn discriminative geometric representations of data from persistence diagrams, common descriptors of Topological Data Analysis.…