Gaussian process classification using posterior linearisation

2018-09-13 · Ángel F. García-Fernández, Filip Tronarp, Simo Särkkä

This paper proposes a new algorithm for Gaussian process classification based on posterior linearisation (PL). In PL, a Gaussian approximation to the posterior density is obtained iteratively using the best possible linearisation of the conditional mean of the labels and accounting for the linearisation error. PL has some theoretical advantages over expectation propagation (EP): all calculated covariance matrices are positive definite and there is a local convergence theorem. In experimental data, PL has better performance than EP with the noisy threshold likelihood and the parallel implementation of the algorithms.

📄 PDF Abstract BibTeX arXiv:1809.04967

Code (0)

등록된 구현이 없습니다.

Tasks

Classification General Classification

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Global Approximate Inference via Local Linearisation for Temporal Gaussian Processes

2019-10-16 · pproximateinference AABI Symposium 2019 12 · William J. Wilkinson, Paul E. Chang, Michael Riis Andersen, Arno Solin

The extended Kalman filter (EKF) is a classical signal processing algorithm which performs efficient approximate Bayesian inference in non-conjugate models by linearising the local measurement function, avoiding the need…

Bayesian Inference Gaussian Processes Variational Inference

Streamlining Prediction in Bayesian Deep Learning

2024-11-27 · Rui Li, Marcus Klasson, Arno Solin, Martin Trapp

The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution. However, efficient computation of inferences, such as predictions, has been largely overlook…

Deep Learning Prediction

Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees

2021-11-02 · William J. Wilkinson, Simo Särkkä, Arno Solin

We formulate natural gradient variational inference (VI), expectation propagation (EP), and posterior linearisation (PL) as extensions of Newton's method for optimising the parameters of a Bayesian posterior distribution…

Bayesian Inference Gaussian Processes State Space Models valid+1

State Space Expectation Propagation: Efficient Inference Schemes for Temporal Gaussian Processes

2020-07-12 · ICML 2020 1 · William J. Wilkinson, Paul E. Chang, Michael Riis Andersen, Arno Solin

We formulate approximate Bayesian inference in non-conjugate temporal and spatio-temporal Gaussian process models as a simple parameter update rule applied during Kalman smoothing. This viewpoint encompasses most inferen…

Bayesian Inference Computational Efficiency Gaussian Processes Variational Inference

Gaussian Process Regression and Classification under Mathematical Constraints with Learning Guarantees

2019-04-21 · Jeremiah Zhe Liu

We introduce constrained Gaussian process (CGP), a Gaussian process model for random functions that allows easy placement of mathematical constrains (e.g., non-negativity, monotonicity, etc) on its sample functions. CGP …

Form General Classification regression