activity
20242026
collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2026

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…

stat.ML2026

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…

stat.ML2025

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…

stat.ML2025

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…

stat.ML2024

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…