19 citations · 19 across the 6 of their papers we have counts for
6 papers
A Framework for Overparameterized Learning
Dávid Terjék, Diego González-Sánchez
A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we pr…
Families of extensions of the Kantorovich-Rubinstein and Lipschitz norms
Dávid Terjék
We propose a family of extensions of the Kantorovich-Rubinstein norm from the space of zero-charge countably additive measures on a compact metric space to the space of all countab…
Optimal transport with -divergence regularization and generalized Sinkhorn algorithm
Dávid Terjék, Diego González-Sánchez
Entropic regularization provides a generalization of the original optimal transport problem. It introduces a penalty term defined by the Kullback-Leibler divergence, making the pro…
A primal representation of the Monge-Kantorovich norm
Dávid Terjék
In this note, following \cite{Chitescuetal2014}, we show that the Monge-Kantorovich norm on the vector space of countably additive measures on a compact metric space has a primal r…
Moreau-Yosida -divergences
Dávid Terjék
Variational representations of -divergences are central to many machine learning algorithms, with Lipschitz constrained variants recently gaining attention. Inspired by this, we…
Adversarial Lipschitz Regularization
Dávid Terjék
Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered s…