Search Results for author:
Found 17 papers, 11 papers with code
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly.
Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
Through empirical evaluation across the benchmark, we demonstrate that our approach outperforms deep-learning generation methods in data generation tasks and remains competitive in data imputation.
Simulation-free Schrödinger bridges via score and flow matching
We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions.
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice.
Unbalanced Optimal Transport meets Sliced-Wasserstein
In parallel, unbalanced OT was designed to allow comparisons of more general positive measures, while being more robust to outliers.
Diffusion models with location-scale noise
Diffusion Models (DMs) are powerful generative models that add Gaussian noise to the data and learn to remove it.
PopulAtion Parameter Averaging (PAPA)
Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging.
Improving and generalizing flow-based generative models with minibatch optimal transport
CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models.
A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes not present in the target domain.
On making optimal transport robust to all outliers
To decrease the influence of these outliers in the transport problem, we propose to either remove them from the problem or to increase the cost of moving them by using the classifier prediction.
Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions.
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Optimal transport distances have found many applications in machine learning for their capacity to compare non-parametric probability distributions.
Minibatch optimal transport distances; analysis and applications
We notably argue that the minibatch strategy comes with appealing properties such as unbiased estimators, gradients and a concentration bound around the expectation, but also with limits: the minibatch OT is not a distance.
Generating Natural Adversarial Hyperspectral examples with a modified Wasserstein GAN
In this paper, we present a new method which is able to generate natural adversarial examples from the true data following the second paradigm.
Learning with minibatch Wasserstein : asymptotic and gradient properties
Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning.
Wasserstein Adversarial Regularization (WAR) on label noise
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping.
Variance Reduced Three Operator Splitting
This is due to the fact that existing methods require to evaluate the proximity operator for the nonsmooth terms, which can be a costly operation for complex penalties.
Optimization and Control 65K10
