6 papers
A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
Samuel Howard, Nikolas Nüsken
Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are ty…
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…
Skew-symmetric schemes for stochastic differential equations with non-Lipschitz drift: an unadjusted Barker algorithm
Yuga Iguchi, Samuel Livingstone, Nikolas Nüsken +2
We propose a new simple and explicit numerical scheme for time-homogeneous stochastic differential equations. The scheme is based on sampling increments at each time step from a sk…
Stein transport for Bayesian inference
Nikolas Nüsken
We introduce , a novel methodology for Bayesian inference designed to efficiently push an ensemble of particles along a predefined curve of tempered proba…
Coherent set identification via direct low rank maximum likelihood estimation
Robert Polzin, Ilja Klebanov, Nikolas Nüsken +1
We analyze connections between two low rank modeling approaches from the last decade for treating dynamical data. The first one is the coherence problem (or coherent set approach),…