paper-with-me

Papers

Probabilistic Linear Solvers for Machine Learning

2020-10-19 · NeurIPS 2020 12 · Jonathan Wenger, Philipp Hennig

Linear systems are the bedrock of virtually all numerical computation. Machine learning poses specific challenges for the solution of such systems due to their scale, characteristic structure, stochasticity and the central role of uncertainty in the field. Unifying earlier work we propose a class of probabilistic linear solvers which jointly infer the matrix, its inverse and the solution from matrix-vector product observations. This class emerges from a fundamental set of desiderata which constrains the space of possible algorithms and recovers the method of conjugate gradients under certain conditions. We demonstrate how to incorporate prior spectral information in order to calibrate uncertainty and experimentally showcase the potential of such solvers for machine learning.

📄 PDF Abstract BibTeX arXiv:2010.09691

Code (1)

JonathanWenger/probabilistic-linear-solvers-for-ml 공식 구현

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs

2026-06-06 · Nathanael Bosch arxiv

Filtering-based probabilistic numerical solvers for ordinary differential equations (ODEs) have been established as a flexible and efficient simulation framework with built-in numerical uncertainty quantification. Howeve…

Active Uncertainty Calibration in Bayesian ODE Solvers

2016-05-11 · Hans Kersting, Philipp Hennig

There is resurging interest, in statistics and machine learning, in solvers for ordinary differential equations (ODEs) that return probability measures instead of point estimates. Recently, Conrad et al. introduced a sam…

Probabilistic Exponential Integrators

2023-05-24 · NeurIPS 2023 11 · Nathanael Bosch, Philipp Hennig, Filip Tronarp

Probabilistic solvers provide a flexible and efficient framework for simulation, uncertainty quantification, and inference in dynamical systems. However, like standard solvers, they suffer performance penalties for certa…

Uncertainty Quantification

Probabilistic Solutions To Ordinary Differential Equations As Non-Linear Bayesian Filtering: A New Perspective

2018-10-08 · Filip Tronarp, Hans Kersting, Simo Särkkä, Philipp Hennig

We formulate probabilistic numerical approximations to solutions of ordinary differential equations (ODEs) as problems in Gaussian process (GP) regression with non-linear measurement functions. This is achieved by defini…

Parallel-in-Time Probabilistic Numerical ODE Solvers

2023-10-02 · Nathanael Bosch, Adrien Corenflos, Fatemeh Yaghoobi, Filip Tronarp 외

Probabilistic numerical solvers for ordinary differential equations (ODEs) treat the numerical simulation of dynamical systems as problems of Bayesian state estimation. Aside from producing posterior distributions over O…

State Estimation