4 papers
Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost
Eliot Beyler, Francis Bach
We introduce Weighted Adjoint Matching, a method to finetune a pretrained diffusion or flow matching model given a differentiable reward. We derive it from Adjoint Matching, which…
Convergence of Deterministic and Stochastic Diffusion-Model Samplers: A Simple Analysis in Wasserstein Distance
Eliot Beyler, Francis Bach
We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling met…
Optimal Denoising in Score-Based Generative Models: The Role of Data Regularity
Eliot Beyler, Francis Bach
Score-based generative models achieve state-of-the-art sampling performance by denoising a distribution perturbed by Gaussian noise. In this paper, we focus on a single determinist…
Variational Inference on the Boolean Hypercube with the Quantum Entropy
Eliot Beyler, Francis Bach
In this paper, we derive variational inference upper-bounds on the log-partition function of pairwise Markov random fields on the Boolean hypercube, based on quantum relaxations of…