ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1402.1754
35
3
v1v2v3v4v5v6 (latest)

Consistent, Two-Stage Sampled Distribution Regression via Mean Embedding

7 February 2014
Z. Szabó
Arthur Gretton
Barnabás Póczós
Bharath K. Sriperumbudur
    OOD
ArXiv (abs)PDFHTML
Abstract

We study the distribution regression problem: regressing to a real-valued response from a probability distribution. Due to the inherent two-stage sampled difficulty of this important machine learning problem---in practise we only have samples from sampled distributions---very little is known about its theoretical properties. In this paper, we propose an algorithmically simple approach to tackle the distribution regression problem: embed the distributions to a reproducing kernel Hilbert space, and learn a ridge regressor from the embeddings to the outputs. Our main contribution is to prove that this technique is consistent in the two-stage sampled setting under fairly mild conditions (for probability distributions on Polish, locally compact Haussdorf spaces on which kernels have been defined). The method gives state-of-the-art results on (i) supervised entropy learning and (ii) the prediction problem of aerosol optical depth based on satellite images.

View on arXiv
Comments on this paper