Minimizing the W2 loss through a distribution-dependent ODE whose time-marginals form an exponentially convergent gradient flow, discretized via Euler scheme with persistent training that outperforms WGANs in experiments.
Santambrogio, Optimal transport for applied mathematicians, vol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generative Modeling by Minimizing the Wasserstein-2 Loss
Minimizing the W2 loss through a distribution-dependent ODE whose time-marginals form an exponentially convergent gradient flow, discretized via Euler scheme with persistent training that outperforms WGANs in experiments.