4 papers · 1 filter
Constructive conditional normalizing flows
Borjan Geshkovski, Domènec Ruiz-Balet
Motivated by applications in conditional sampling, given a probability measure and a diffeomorphism , we consider the problem of simultaneously approximating and the…
Measure-to-measure interpolation using Transformers
Borjan Geshkovski, Philippe Rigollet, Domènec Ruiz-Balet
Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-p…
Constructive approximate transport maps with normalizing flows
Antonio Ãlvarez-López, Borjan Geshkovski, Domènec Ruiz-Balet
We study an approximate controllability problem for the continuity equation and its application to constructing transport maps with normalizing flows. Specifically, we construct ti…
Attention's forward pass and Frank-Wolfe
Albert Alcalde, Borjan Geshkovski, Domènec Ruiz-Balet
We study the hardmax limit of self-attention dynamics for token embeddings obtained in the zero-temperature () regime, and relate it to the finite- setting. In th…