38 citations · 87 across the 11 of their papers we have counts for
13 papers
The Fenchel Game of Underdamped Langevin Dynamics: Insights into Accelerated Convergence
Alexandra Borkowski, Nikolas Nüsken
For governed by suitably damped underdamped Langevin dynamics, we quantify the convergence in KL divergence of the positional marginal to a -strongly log-concave tar…
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…
Measure transport with kernel mean embeddings
L. Wang, N. Nüsken
Kalman filters constitute a scalable and robust methodology for approximate Bayesian inference, matching first and second order moments of the target posterior. To improve the accu…
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),…
From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs
Lorenz Richter, Leon Sallandt, Nikolas Nüsken
The numerical approximation of partial differential equations (PDEs) poses formidable challenges in high dimensions since classical grid-based methods suffer from the so-called cur…
Rough McKean-Vlasov dynamics for robust ensemble Kalman filtering
Michele Coghi, Torstein Nilssen, Nikolas Nüsken +1
Motivated by the challenge of incorporating data into misspecified and multiscale dynamical models, we study a McKean-Vlasov equation that contains the data stream as a common driv…
Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space
Nikolas Nüsken, Lorenz Richter
Optimal control of diffusion processes is intimately connected to the problem of solving certain Hamilton-Jacobi-Bellman equations. Building on recent machine learning inspired app…
On the geometry of Stein variational gradient descent
A. Duncan, N. Nuesken, L. Szpruch
Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gr…
State and Parameter Estimation from Observed Signal Increments
Nikolas Nüsken, Sebastian Reich, Paul J. Rozdeba
The success of the ensemble Kalman filter has triggered a strong interest in expanding its scope beyond classical state estimation problems. In this paper, we focus on continuous-t…
Hypocoercivity of Piecewise Deterministic Markov Process-Monte Carlo
Christophe Andrieu, Alain Durmus, Nikolas Nüsken +1
In this work, we establish -exponential convergence for a broad class of Piecewise Deterministic Markov Processes recently proposed in the context of Markov Process M…
Constructing sampling schemes via coupling: Markov semigroups and optimal transport
N. Nuesken, G. A. Pavliotis
In this paper we develop a general framework for constructing and analysing coupled Markov chain Monte Carlo samplers, allowing for both (possibly degenerate) diffusion and piecewi…
Using Perturbed Underdamped Langevin Dynamics to Efficiently Sample from Probability Distributions
A. B. Duncan, N. Nuesken, G. A. Pavliotis
In this paper we introduce and analyse Langevin samplers that consist of perturbations of the standard underdamped Langevin dynamics. The perturbed dynamics is such that its invari…