4 citations · 8 across the 11 of their papers we have counts for
12 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…
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…
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…
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…
Tweedie Moment Projected Diffusions For Inverse Problems
Benjamin Boys, Mark Girolami, Jakiw Pidstrigach +3
Diffusion generative models unlock new possibilities for inverse problems as they allow for the incorporation of strong empirical priors in scientific inference. Recently, diffusio…
Affine Invariant Ensemble Transform Methods to Improve Predictive Uncertainty in Neural Networks
Diksha Bhandari, Jakiw Pidstrigach, Sebastian Reich
We consider the problem of performing Bayesian inference for logistic regression using appropriate extensions of the ensemble Kalman filter. Two interacting particle systems are pr…
Infinite-Dimensional Diffusion Models
Jakiw Pidstrigach, Youssef Marzouk, Sebastian Reich +1
Diffusion models have had a profound impact on many application areas, including those where data are intrinsically infinite-dimensional, such as images or time series. The standar…
Score-Based Generative Models Detect Manifolds
Jakiw Pidstrigach
Score-based generative models (SGMs) need to approximate the scores of the intermediate distributions as well as the final distribution of the forward proce…
Affine-invariant ensemble transform methods for logistic regression
Jakiw Pidstrigach, Sebastian Reich
We investigate the application of ensemble transform approaches to Bayesian inference of logistic regression problems. Our approach relies on appropriate extensions of the popular…
Convergence of Preconditioned Hamiltonian Monte Carlo on Hilbert Spaces
Jakiw Pidstrigach
In this article, we consider the preconditioned Hamiltonian Monte Carlo (pHMC) algorithm defined directly on an infinite-dimensional Hilbert space. In this context, and under a con…