2 papers
cs.LG2025
Unveiling Transformer Perception by Exploring Input Manifolds
Alessandro Benfenati, Alfio Ferrara, Alessio Marta +2
This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical the…
cs.LG2025
Estimating Dataset Dimension via Singular Metrics under the Manifold Hypothesis: Application to Inverse Problems
Paola Causin, Alessio Marta
High-dimensional datasets often exhibit low-dimensional geometric structures, as suggested by the manifold hypothesis, which implies that data lie on a smooth manifold embedded in…