Identifiability of Deep Polynomial Neural Networks

NeurIPSOral2025

Authors: Konstantin Usevich, Ricardo Augusto Borsoi, Clara Dérand, Marianne Clausel
Affiliation: CNRS
Venue: NeurIPS 2025
Track: Oral

TL;DR

We provide necessary and sufficient conditions for the identifiability deep polinomial neural networks.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All NeurIPS 2025 Oral papers · Browse the whole archive