10 papers
Latent Guided Sampling for Combinatorial Optimization
Sobihan Surendran, Adeline Fermanian, Sylvain Le Corff
Combinatorial Optimization problems are widespread in domains such as logistics, manufacturing, and drug discovery, yet their NP-hard nature makes them computationally challenging.…
On Forgetting and Stability of Score-based Generative models
Stanislas Strasman, Gabriel Cardoso, Sylvain Le Corff +2
Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning. This paper provides quantitative bounds on the sampling…
Independent Component Discovery in Temporal Count Data
Alexandre Chaussard, Anna Bonnet, Sylvain Le Corff
Advances in data collection are producing growing volumes of temporal count observations, making adapted modeling increasingly necessary. In this work, we introduce a generative fr…
Diffusion posterior sampling for simulation-based inference in tall data settings
Julia Linhart, Gabriel Victorino Cardoso, Alexandre Gramfort +2
Identifying the parameters of a non-linear model that best explain observed data is a core task across scientific fields. When such models rely on complex simulators, evaluating th…
Convergence of Multi-Level Markov Chain Monte Carlo Adaptive Stochastic Gradient Algorithms
Antoine Godichon-Baggioni, Gabriel Lang, Sylvain Le Corff +2
Stochastic optimization in learning and inference often relies on Markov chain Monte Carlo (MCMC) to approximate gradients when exact computation is intractable. However, finite-ti…
Theoretical Convergence Guarantees for Variational Autoencoders
Sobihan Surendran, Antoine Godichon-Baggioni, Sylvain Le Corff
Variational Autoencoders (VAE) are popular generative models used to sample from complex data distributions. Despite their empirical success in various machine learning tasks, sign…