9 papers
Itô maps for any-step SDEs
Zhengkai Pan, Peter Potaptchik, Wenxi Yao +2
Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics. These methods rely on learning from ordinary differential equa…
Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models
Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2
Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL…
Control Consistency Losses for Diffusion Bridges
Samuel Howard, Nikolas Nüsken, Jakiw Pidstrigach
Simulating the conditioned dynamics of diffusion processes, given their initial and terminal states, is an important but challenging problem in the sciences. The difficulty is part…
Sensitivity Analysis for Climate Science with Generative Flow Models
Alex Dobra, Jakiw Pidstrigach, Tim Reichelt +6
Sensitivity analysis is a cornerstone of climate science, essential for understanding phenomena ranging from storm intensity to long-term climate feedbacks. However, computing thes…
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
Tyler Farghly, Peter Potaptchik, Samuel Howard +2
Diffusion models have achieved state-of-the-art performance, demonstrating remarkable generalisation capabilities across diverse domains. However, the mechanisms underpinning these…
Conditioning Diffusions Using Malliavin Calculus
Jakiw Pidstrigach, Elizabeth Baker, Carles Domingo-Enrich +2
In generative modelling and stochastic optimal control, a central computational task is to modify a reference diffusion process to maximise a given terminal-time reward. Most exist…