Score Operator Newton transport
Not on the map. Why?
Abstract (arXiv)
We propose a new approach for sampling and Bayesian computation that uses the score of the target distribution to construct a transport from a given reference distribution to the target. Our approach is an infinite-dimensional Newton method, involving a linear PDE, for finding a zero of a ``score-residual'' operator. We prove sufficient conditions for convergence to a valid transport map. Our Newton iterates can be computed by exploiting fast solvers for elliptic PDEs, resulting in new algorithms for Bayesian inference and other sampling tasks. We identify elementary settings where score-operator Newton transport achieves fast convergence while avoiding mode collapse.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 76 references that are in the map. First posted on arXiv 16 May 2023.
Builds on
24 of 76 references.
References · 24
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2022Generative Adversarial Networkscited by 5,603
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2018Neural Ordinary Differential Equationscited by 3,733
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
- 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
- 2019An Introduction to Variational Autoencoderscited by 997
- 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
- 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 581
- 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
- 2018Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problemcited by 123
12 more
- 2020Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimizationcited by 89
- 2019On the geometry of Stein variational gradient descentcited by 82
- 2020SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergencecited by 64
- 2018A Stein variational Newton methodcited by 49
- 2021Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimalitycited by 40
- 2020Projected Stein Variational Gradient Descentcited by 33
- 2021Learning elliptic partial differential equations with randomized linear algebracited by 29
- 2021Interpolating between BSDEs and PINNs: deep learning for elliptic and parabolic boundary value problemscited by 21
- 2021q-Paths: Generalizing the Geometric Annealing Path using Power Meanscited by 12
- 2019A stochastic version of Stein Variational Gradient Descent for efficient samplingcited by 10
- 2017Stein Variational Adaptive Importance Samplingcited by 7
- 2020Adaptive regularisation for ensemble Kalman inversioncited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.