Ensemble Kalman inversion: a derivative-free technique for machine learning tasks

DOI10.1088/1361-6420/ab1c3azbMath1430.68266arXiv1808.03620OpenAlexW2949400887WikidataQ127968194 ScholiaQ127968194MaRDI QIDQ5197869

Nikola B. Kovachki, Andrew M. Stuart

Publication date: 20 September 2019

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.03620

zbMATH Keywords

machine learningderivative-free optimizationdeep learningensemble Kalman filteringensemble Kalman inversion

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Signal detection and filtering (aspects of stochastic processes) (60G35)

Related Items (35)

Calibrate, emulate, sample ⋮ Derivative-Free Bayesian Inversion Using Multiscale Dynamics ⋮ Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis ⋮ Ensemble Kalman method for learning turbulence models from indirect observation data ⋮ Recent trends on nonlinear filtering for inverse problems ⋮ Harmonic analysis on graphs via Bratteli diagrams and path-space measures ⋮ Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion ⋮ Mean-field and kinetic descriptions of neural differential equations ⋮ Ensemble Gradient for Learning Turbulence Models from Indirect Observations ⋮ Convergence acceleration of ensemble Kalman inversion in nonlinear settings ⋮ A Stabilization of a Continuous Limit of the Ensemble Kalman Inversion ⋮ Efficient estimation of hydraulic conductivity heterogeneity with non-redundant measurement information ⋮ Ensemble Inference Methods for Models With Noisy and Expensive Likelihoods ⋮ Iterated Kalman methodology for inverse problems ⋮ Localized ensemble Kalman inversion ⋮ On convergence rates of adaptive ensemble Kalman inversion for linear ill-posed problems ⋮ Deep limits of residual neural networks ⋮ Consensus‐based sampling ⋮ Continuous limits of residual neural networks in case of large input data ⋮ Identifying a fractional order and a time-dependent coefficient in a time-fractional diffusion wave equation ⋮ Adaptive Ensemble Kalman Inversion with Statistical Linearization ⋮ Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler ⋮ Tikhonov Regularization within Ensemble Kalman Inversion ⋮ Subsampling in ensemble Kalman inversion ⋮ Hierarchical ensemble Kalman methods with sparsity-promoting generalized gamma hyperpriors ⋮ Affine-invariant ensemble transform methods for logistic regression ⋮ Adaptive regularisation for ensemble Kalman inversion ⋮ $l_p$ Regularization for Ensemble Kalman Inversion ⋮ Affine Invariant Interacting Langevin Dynamics for Bayesian Inference ⋮ Discrete gradients for computational Bayesian inference ⋮ Analysis of stochastic gradient descent in continuous time ⋮ Online learning of both state and dynamics using ensemble Kalman filters ⋮ Iterative ensemble Kalman methods: a unified perspective with some new variants ⋮ Fokker--Planck Particle Systems for Bayesian Inference: Computational Approaches ⋮ Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models

Uses Software

• EnKF
• darch
• MNIST
• PMTK
• PyTorch
• ImageNet
• AdaGrad
• Adam
• CNN-RNN
• Fashion-MNIST
• AlexNet
• FitNets
• Entropy-SGD

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• AlexNet
• Nonparametric stochastic approximation with large step-sizes
• A Bayesian level set method for geometric inverse problems
• Minimizing finite sums with the stochastic average gradient
• Data. A collection of problems from many fields for the student and research worker
• FitNets
• Ensemble Kalman methods for inverse problems
• Reducing the Dimensionality of Data with Neural Networks
• Uncertainty Quantification in Graph-Based Classification of High Dimensional Data
• Analysis of the Ensemble and Polynomial Chaos Kalman Filters in Bayesian Inverse Problems
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• Computational Methods for Inverse Problems
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• Data Assimilation
• Analysis of the Ensemble Kalman Filter for Inverse Problems
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Stochastic Estimation of the Maximum of a Regression Function
• A Stochastic Approximation Method
• Entropy-SGD: biasing gradient descent into wide valleys

This page was built for publication: Ensemble Kalman inversion: a derivative-free technique for machine learning tasks