paper-with-me

Papers

On the Laplace Approximation as Model Selection Criterion for Gaussian Processes

2024-03-14 · Andreas Besginow, Jan David Hüwel, Thomas Pawellek, Christian Beecks, Markus Lange-Hegermann

Model selection aims to find the best model in terms of accuracy, interpretability or simplicity, preferably all at once. In this work, we focus on evaluating model performance of Gaussian process models, i.e. finding a metric that provides the best trade-off between all those criteria. While previous work considers metrics like the likelihood, AIC or dynamic nested sampling, they either lack performance or have significant runtime issues, which severely limits applicability. We address these challenges by introducing multiple metrics based on the Laplace approximation, where we overcome a severe inconsistency occuring during naive application of the Laplace approximation. Experiments show that our metrics are comparable in quality to the gold standard dynamic nested sampling without compromising for computational speed. Our model selection criteria allow significantly faster and high quality model selection of Gaussian process models.

📄 PDF Abstract BibTeX arXiv:2403.09215

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian ProcessesModel Selection

Methods 이 논문이 사용한 방법론

Focus 설명 없음
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…

Similar Papers 제목 키워드 기반

Model Selection for Gaussian Process Regression by Approximation Set Coding

2016-10-04 · Benjamin Fischer, Nico Gorbach, Stefan Bauer, Yatao Bian 외

Gaussian processes are powerful, yet analytically tractable models for supervised learning. A Gaussian process is characterized by a mean function and a covariance function (kernel), which are determined by a model selec…

Gaussian ProcessesModel Selectionregression

Approximately Bayes-Optimal Pseudo Label Selection

2023-02-17 · Julian Rodemann, Jann Goschenhofer, Emilio Dorigatti, Thomas Nagler 외

Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). The selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final mode…

Additive modelsPseudo Label

Differentially Private Regression and Classification with Sparse Gaussian Processes

2019-09-19 · Michael Thomas Smith, Mauricio A. Alvarez, Neil D. Lawrence

A continuing challenge for machine learning is providing methods to perform computation on data while ensuring the data remains private. In this paper we build on the provable privacy guarantees of differential privacy w…

ClassificationGaussian ProcessesGeneral Classificationregression

Laplace Matching for fast Approximate Inference in Latent Gaussian Models

2021-05-07 · Marius Hobbhahn, Philipp Hennig

Bayesian inference on non-Gaussian data is often non-analytic and requires computationally expensive approximations such as sampling or variational inference. We propose an approximate inference framework primarily desig…

Bayesian InferenceGaussian ProcessesVariational Inference

Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks

2020-07-21 · Alexander Immer

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian dee…

Deep LearningGaussian Processes