paper-with-me

Papers

Score Operator Newton transport

2023-05-16 · Nisha Chandramoorthy, Florian Schaefer, Youssef Marzouk

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.

📄 PDF Abstract BibTeX arXiv:2305.09792

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferencevalidVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Riemannian stochastic quasi-Newton algorithm with variance reduction and its convergence analysis

2017-03-15 · Hiroyuki Kasai, Hiroyuki Sato, Bamdev Mishra

Stochastic variance reduction algorithms have recently become popular for minimizing the average of a large, but finite number of loss functions. The present paper proposes a Riemannian stochastic quasi-Newton algorithm …

Low-Rank Matrix CompletionMatrix Completion

Solving Newton's Equations of Motion with Large Timesteps using Recurrent Neural Networks based Operators

2020-04-12 · JCS Kadupitiya, Geoffrey C. Fox, Vikram Jadhao

Classical molecular dynamics simulations are based on solving Newton's equations of motion. Using a small timestep, numerical integrators such as Verlet generate trajectories of particles as solutions to Newton's equatio…

A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers

2025-11-11 · Youngkyu Lee, Shanqing Liu, Jerome Darbon, George Em Karniadakis arxiv

We propose a novel neural preconditioned Newton (NP-Newton) method for solving parametric nonlinear systems of equations. To overcome the stagnation or instability of Newton iterations caused by unbalanced nonlinearities…

Computational Efficiency

Neural-Initialized Newton: Accelerating Nonlinear Finite Elements via Operator Learning

2025-11-10 · Kianoosh Taghikhani, Yusuke Yamazaki, Jerry Paul Varghese, Markus Apel 외 arxiv

We propose a Newton-based scheme, initialized by neural operator predictions, to accelerate the parametric solution of nonlinear problems in computational solid mechanics. First, a physics informed conditional neural fie…

Differentiable Top-k Operator with Optimal Transport

2020-02-16 · Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai 외

The top-k operation, i.e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining. Howeve…

Information RetrievalRetrieval