{
  "id": "2505.11355",
  "version": "v1",
  "published": "2025-05-16T15:18:15.000Z",
  "updated": "2025-05-16T15:18:15.000Z",
  "title": "STRIDE: Sparse Techniques for Regression in Deep Gaussian Processes",
  "authors": [
    "Simon Urbainczyk",
    "Aretha L. Teckentrup",
    "Jonas Latz"
  ],
  "categories": [
    "stat.ML",
    "cs.LG",
    "stat.CO"
  ],
  "abstract": "Gaussian processes (GPs) have gained popularity as flexible machine learning models for regression and function approximation with an in-built method for uncertainty quantification. However, GPs suffer when the amount of training data is large or when the underlying function contains multi-scale features that are difficult to represent by a stationary kernel. To address the former, training of GPs with large-scale data is often performed through inducing point approximations (also known as sparse GP regression (GPR)), where the size of the covariance matrices in GPR is reduced considerably through a greedy search on the data set. To aid the latter, deep GPs have gained traction as hierarchical models that resolve multi-scale features by combining multiple GPs. Posterior inference in deep GPs requires a sampling or, more usual, a variational approximation. Variational approximations lead to large-scale stochastic, non-convex optimisation problems and the resulting approximation tends to represent uncertainty incorrectly. In this work, we combine variational learning with MCMC to develop a particle-based expectation-maximisation method to simultaneously find inducing points within the large-scale data (variationally) and accurately train the GPs (sampling-based). The result is a highly efficient and accurate methodology for deep GP training on large-scale data. We test our method on standard benchmark problems.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2025-05-16T15:18:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep gaussian processes",
      "sparse techniques",
      "deep gp",
      "large-scale data",
      "variational approximation"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}