Tabular data is hard to acquire and is subject to missing values. This p...
We present simulation-free score and flow matching ([SF]^2M), a
simulati...
Understanding the optimization dynamics of neural networks is necessary ...
Optimal transport (OT) has emerged as a powerful framework to compare
pr...
Diffusion Models (DMs) are powerful generative models that add Gaussian ...
Ensemble methods combine the predictions of multiple models to improve
p...
Continuous normalizing flows (CNFs) are an attractive generative modelin...
Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled targe...
Optimal transport (OT) is known to be sensitive against outliers because...
It is common in computer vision to be confronted with domain shift: imag...
Optimal transport distances have found many applications in machine lear...
Optimal transport distances have become a classic tool to compare probab...
Adversarial examples are a hot topic due to their abilities to fool a
cl...
Optimal transport distances are powerful tools to compare probability
di...
Noisy labels often occur in vision datasets, especially when they are is...