Asymmetric kernel in Gaussian Processes for learning target variance

This work incorporates the multi-modality of the data distribution into a Gaussian Process regression model. We approach the problem from a discriminative perspective by learning, jointly over the training data, the target space variance in the neighborhood of a certain sample through metric learning. We start by using data centers rather than all training samples. Subsequently, each center selects an individualized kernel metric. This enables each center to adjust the kernel space in its vicinity in correspondence with the topology of the targets --- a multi-modal approach. We additionally add descriptiveness by allowing each center to learn a precision matrix. We demonstrate empirically the reliability of the model.

• Publication year

  2018

• Venue

  Pattern Recognition Letters

• Publication date

  2018-03-19

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1016/J.PATREC.2018.02.026arXiv 1803.06952
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Large scale Gaussian Process for overlap-based object proposal scoring

  2016cited by this paper
• Counting Everyday Objects in Everyday Scenes

  2016cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data

  2015influential reference
• Metric Learning

  2015cited by this paper
• ImageNet Large Scale Visual Recognition Challenge

  2014cited by this paper
• Gaussian Process Learning: A Divide-and-Conquer Approach

  2014cited by this paper
• Fast Allocation of Gaussian Process Experts

  2014cited by this paper
• Stress functions for nonlinear dimension reduction, proximity analysis, and graph drawing

  2013cited by this paper
• Variational Inference for Mahalanobis Distance Metrics in Gaussian Process Regression

  2013influential reference
• On the importance of initialization and momentum in deep learning

  2013cited by this paper
• Efficient Optimization for Sparse Gaussian Process Regression

  2013cited by this paper
• Gaussian Processes for Big Data

  2013cited by this paper
• Kernel regression with sparse metric learning

  2013cited by this paper
• Counting People With Low-Level Features and Bayesian Regression

  2012influential reference
• Large scale metric learning from equivalence constraints

  2012cited by this paper
• Non-linear Metric Learning

  2012cited by this paper
• Large-Scale Gaussian Process Classification with Flexible Adaptive Histogram Kernels

  2012cited by this paper
• Variational Heteroscedastic Gaussian Process Regression

  2011cited by this paper
• Online Sparse Gaussian Process Regression and Its Applications

  2011cited by this paper
• Overlapping Mixtures of Gaussian Processes for the Data Association Problem

  2011cited by this paper
• What you saw is not what you get: Domain adaptation using asymmetric kernel transforms

  2011cited by this paper
• Bayesian Gaussian Process Latent Variable Model

  2010cited by this paper
• Asymmetric Kernel Learning

  2010influential reference
• Variational Learning of Inducing Variables in Sparse Gaussian Processes

  2009cited by this paper
• Metric and Kernel Learning Using a Linear Transformation

  2009cited by this paper
• Variational Mixture of Gaussian Process Experts

  2008cited by this paper
• A discriminatively trained, multiscale, deformable part model

  2008influential reference
• Greedy Block Coordinate Descent for Large Scale Gaussian Process Regression

  2008cited by this paper
• Local and global sparse Gaussian process approximations

  2007cited by this paper
• Random Features for Large-Scale Kernel Machines

  2007cited by this paper
• Most likely heteroscedastic Gaussian process regression

  2007cited by this paper
• Metric Learning for Kernel Regression

  2007cited by this paper
• The PASCAL Visual Object Classes Challenge

  2006cited by this paper
• The Pascal Visual Object Classes Challenge 2006 ( VOC 2006 ) Results

  2006cited by this paper
• Approximate inference for robust Gaussian process regression

  2005cited by this paper
• Sparse Gaussian Processes using Pseudo-inputs

  2005cited by this paper
• The 2005 PASCAL Visual Object Classes Challenge

  2005cited by this paper
• Metric Learning by Collapsing Classes

  2005cited by this paper
• An Alternative Infinite Mixture Of Gaussian Process Experts

  2005cited by this paper
• A Unifying View of Sparse Approximate Gaussian Process Regression

  2005cited by this paper
• Distance Metric Learning for Large Margin Nearest Neighbor Classification

  2005cited by this paper
• Histograms of oriented gradients for human detection

  2005influential reference
• Asymmetric kernel regression

  2004cited by this paper
• Nonstationary Covariance Functions for Gaussian Process Regression

  2003cited by this paper
• Fast Forward Selection to Speed Up Sparse Gaussian Process Regression

  2003cited by this paper
• Gaussian Processes in Machine Learning

  2003influential reference
• Distance Metric Learning with Application to Clustering with Side-Information

  2002cited by this paper
• Fast Sparse Gaussian Process Methods: The Informative Vector Machine

  2002cited by this paper
• Sparse On-Line Gaussian Processes

  2002cited by this paper
• Infinite Mixtures of Gaussian Process Experts

  2001cited by this paper
• Mixtures of Gaussian Processes

  2000cited by this paper
• Discovering Hidden Features with Gaussian Processes Regression

  1998cited by this paper
• Support Vector Classi er with Asymmetric Kernel Functions

  1998cited by this paper

• Mixtures of Gaussian processes for robotic environmental monitoring of emission sources

  2025cites this paper
• Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning

  2024cites this paper
• Diffusion Representation for Asymmetric Kernels via Magnetic Transform

  2023cites this paper
• Learning With Asymmetric Kernels: Least Squares and Feature Interpretation

  2022cites this paper
• A Robust Asymmetric Kernel Function for Bayesian Optimization, With Application to Image Defect Detection in Manufacturing Systems

  2021cites this paper
• Continuous learning in computer vision

  2017cites this paper