34 citations · 162 across the 17 of their papers we have counts for
17 papers
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
Guillaume Huguet, James Vuckovic, Kilian Fatras +9
Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in turn determined by their amino acid sequences…
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Avishek Joey Bose, Tara Akhound-Sadegh, Guillaume Huguet +7
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce FoldFlow, a series of novel…
Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
Alexia Jolicoeur-Martineau, Kilian Fatras, Tal Kachman
Tabular data is hard to acquire and is subject to missing values. This paper introduces a novel approach for generating and imputing mixed-type (continuous and categorical) tabular…
Simulation-free Schrödinger bridges via score and flow matching
Alexander Tong, Nikolay Malkin, Kilian Fatras +5
We present simulation-free score and flow matching ([SF]M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and…
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras +1
Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-order optimization algorithms are known to…
Slicing Unbalanced Optimal Transport
Clément Bonet, Kimia Nadjahi, Thibault Séjourné +2
Optimal transport (OT) is a powerful framework to compare probability measures, a fundamental task in many statistical and machine learning problems. Substantial advances have been…
Diffusion models with location-scale noise
Alexia Jolicoeur-Martineau, Kilian Fatras, Ke Li +1
Diffusion Models (DMs) are powerful generative models that add Gaussian noise to the data and learn to remove it. We wanted to determine which noise distribution (Gaussian or non-G…
PopulAtion Parameter Averaging (PAPA)
Alexia Jolicoeur-Martineau, Emy Gervais, Kilian Fatras +2
Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs at inference time. To avoid these costs,…
Improving and generalizing flow-based generative models with minibatch optimal transport
Alexander Tong, Kilian Fatras, Nikolay Malkin +5
Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their simulation-based maximum likelihood traini…
On making optimal transport robust to all outliers
Kilian Fatras
Optimal transport (OT) is known to be sensitive against outliers because of its marginal constraints. Outlier robust OT variants have been proposed based on the definition that out…
Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas
It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to c…
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Kilian Fatras, Thibault Séjourné, Nicolas Courty +1
Optimal transport distances have found many applications in machine learning for their capacity to compare non-parametric probability distributions. Yet their algorithmic complexit…
Minibatch optimal transport distances; analysis and applications
Kilian Fatras, Younes Zine, Szymon Majewski +3
Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. Yet, despite recent algorithmic de…
Generating Natural Adversarial Hyperspectral examples with a modified Wasserstein GAN
Jean-Christophe Burnel, Kilian Fatras, Nicolas Courty
Adversarial examples are a hot topic due to their abilities to fool a classifier's prediction. There are two strategies to create such examples, one uses the attacked classifier's…
Learning with minibatch Wasserstein : asymptotic and gradient properties
Kilian Fatras, Younes Zine, Rémi Flamary +2
Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents…
Wasserstein Adversarial Regularization (WAR) on label noise
Kilian Fatras, Bharath Bhushan Damodaran, Sylvain Lobry +3
Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning ro…
Proximal Splitting Meets Variance Reduction
Fabian Pedregosa, Kilian Fatras, Mattia Casotto
Despite the rise to fame of incremental variance-reduced methods in recent years, their use in nonsmooth optimization is still limited to few simple cases. This is due to the fact…