Hierarchical Gaussian Processes with Wasserstein-2 Kernels
Stacking Gaussian Processes severely diminishes the model's ability to detect outliers, which when combined with non-zero mean functions, further extrapolates low non-parametric variance to low training data density regions. We propose a hybrid kernel inspired from Varifold theory, operating in both Euclidean and Wasserstein space. We posit that directly taking into account the variance in the computation of Wasserstein-2 distances is of key importance towards maintaining outlier status throughout the hierarchy. We show improved performance on medium and large scale datasets and enhanced out-of-distribution detection on both toy and real data.
Code (0)
등록된 구현이 없습니다.
Tasks
Gaussian ProcessesOut-of-Distribution DetectionSimilar Papers 제목 키워드 기반
A Gaussian Process Regression Model for Distribution Inputs
Monge-Kantorovich distances, otherwise known as Wasserstein distances, have received a growing attention in statistics and machine learning as a powerful discrepancy measure for probability distributions. In this paper, …
BIG-bench Machine LearningGaussian ProcessesmodelregressionDistributional Gaussian Process Layers for Outlier Detection in Image Segmentation
We propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty. This directly rep…
Gaussian ProcessesImage SegmentationOutlier DetectionOut-of-Distribution Detection+2Rate of Convergence of Polynomial Networks to Gaussian Processes
We examine one-hidden-layer neural networks with random weights. It is well-known that in the limit of infinitely many neurons they simplify to Gaussian processes. For networks with a polynomial activation, we demonstrat…
Gaussian ProcessesDistributional Gaussian Processes Layers for Out-of-Distribution Detection
Machine learning models deployed on medical imaging tasks must be equipped with out-of-distribution detection capabilities in order to avoid erroneous predictions. It is unsure whether out-of-distribution detection model…
Gaussian ProcessesOut-of-Distribution DetectionSegmentationSentiment analysis with genetically evolved Gaussian kernels
Sentiment analysis consists of evaluating opinions or statements from the analysis of text. Among the methods used to estimate the degree in which a text expresses a given sentiment, are those based on Gaussian Processes…
Gaussian ProcessesSentiment Analysis