1 code implementation • 2 May 2024 • Rafael Elberg, Denis Parra, Mircea Petrache
Image and multimodal machine learning tasks are very challenging to solve in the case of poorly distributed data.
1 code implementation • 22 Feb 2024 • Rolando Kindelan Nuñez, Mircea Petrache, Mauricio Cerda, Nancy Hitschfeld
In this work we introduce a class of pseudodistances called Extended Topological Pseudodistances (ETD)s, which have tunable complexity, and can approximate Sliced and classical Wasserstein distances at the high-complexity extreme, while being computationally lighter and close to Persistence Statistics at the lower complexity extreme, and thus allow users to interpolate between the two metrics.
no code implementations • 2 Feb 2024 • Mircea Petrache, Shubhendu Trivedi
Compositional generalization is one of the main properties which differentiates lexical learning in humans from state-of-art neural networks.
no code implementations • 22 Mar 2023 • Valentino Delle Rose, Alexander Kozachinskiy, Cristóbal Rojas, Mircea Petrache, Pablo Barceló
Our main result states that the $(d-1)$-dimensional WL test is complete for point clouds in $d$-dimensional Euclidean space, for any $d\ge 2$, and that only three iterations of the test suffice.
no code implementations • 28 Jan 2021 • Giacomo Del Nin, Mircea Petrache
We prove discrete-to-continuum convergence of interaction energies defined on lattices in the Euclidean space (with interactions beyond nearest neighbours) to a crystalline perimeter, and we discuss the possible Wulff shapes obtainable in this way.
Metric Geometry Mathematical Physics Analysis of PDEs Mathematical Physics 49Q20, 49J45 (primary), 49Q10, 52B11, 52C07, 52C22, 52C23 (secondary)