51 citations · 211 across the 29 of their papers we have counts for
4 papers · 1 filter
Approximation Rates for Metaplectic Neural Networks
Ahmed Abdeljawad, Marcello Carioni, Elena Cordero
In this paper we develop quantitative approximation results for shallow neural networks constructed using a dictionary based on metaplectic operators. First, we extend the concept…
Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
Alex Massucco, Leonardo Del Grande, Marcello Carioni +2
In recent years, transformer architectures have revolutionized the field of language processing, opening the door to previously unforeseen possibilities. However, from a theoretica…
Sinkhorn AutoEncoders
Giorgio Patrini, Rianne van den Berg, Patrick Forré +5
Optimal transport offers an alternative to maximum likelihood for learning generative autoencoding models. We show that minimizing the p-Wasserstein distance between the generator…
Loss factorization, weakly supervised learning and label noise robustness
Giorgio Patrini, Frank Nielsen, Richard Nock +1
We prove that the empirical risk of most well-known loss functions factors into a linear term aggregating all labels with a term that is label free, and can further be expressed by…