5 papers · 1 filter
Online Decision-Focused Learning
Aymeric Capitaine, Maxime Haddouche, Eric Moulines +3
Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks. Instead of merely optimizing for…
Categorical Reparameterization with Denoising Diffusion models
Samson Gourevitch, Alain Durmus, Eric Moulines +2
Learning models with categorical variables requires optimizing expectations over discrete distributions, a setting in which stochastic gradient-based optimization is challenging du…
Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey
Yazid Janati, Alain Durmus, Jimmy Olsson +1
Diffusion models enable the synthesis of highly accurate samples from complex distributions and have become foundational in generative modeling. Recently, they have demonstrated si…
Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
Badr Moufad, Yazid Janati, Alain Durmus +3
Classifier-Free Guidance (CFG) is a widely used technique for improving conditional diffusion models by linearly combining the outputs of conditional and unconditional denoisers. W…
Optimal Design for Reward Modeling in RLHF
Antoine Scheid, Etienne Boursier, Alain Durmus +4
Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large datas…