Gaussian Process Regression

Also known as GP

Overview

Gaussian process regression (GPR) places a probability distribution over functions, with kernels encoding assumptions such as smoothness, periodicity, or shared structure; conditioning on observations yields predictions and uncertainty, especially useful when data are scarce or decisions depend on confidence. Research develops richer models—including nonstationary, additive, multi-output, deep, and physics-informed GPs—and applies them to time series, spatial fields, dynamical systems, scientific surrogates, and Bayesian optimization. Because exact inference scales cubically with sample count, scalable approaches use inducing points and variational inference, nearest-neighbor or Vecchia approximations, sparse and low-rank kernels, and streaming or distributed updates. A central tension is balancing expressive models and calibrated uncertainty against computational cost and sensitivity to kernel and hyperparameter choices; reliable uncertainty under misspecification and scalable high-dimensional inference remain open challenges.

Latest papers

CardsList

121 papers13 papers in the last four weeks, down 24% on the four weeks before. 0.1% of all new papers.

  1. Optimal Kernel Learning for Gaussian Process Models with High-Dimensional Input

    Feb 23, 2025Lulu Kang, Minshen XuGaussian Process RegressionKernel Methods