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. 2305.02252
20
4

An Adaptive Algorithm for Learning with Unknown Distribution Drift

3 May 2023
Alessio Mazzetto
E. Upfal
    OOD
ArXivPDFHTML
Abstract

We develop and analyze a general technique for learning with an unknown distribution drift. Given a sequence of independent observations from the last TTT steps of a drifting distribution, our algorithm agnostically learns a family of functions with respect to the current distribution at time TTT. Unlike previous work, our technique does not require prior knowledge about the magnitude of the drift. Instead, the algorithm adapts to the sample data. Without explicitly estimating the drift, the algorithm learns a family of functions with almost the same error as a learning algorithm that knows the magnitude of the drift in advance. Furthermore, since our algorithm adapts to the data, it can guarantee a better learning error than an algorithm that relies on loose bounds on the drift. We demonstrate the application of our technique in two fundamental learning scenarios: binary classification and linear regression.

View on arXiv
Comments on this paper