mlsanityData to 7 Oct 2026

Universally Consistent Online Learning with Arbitrarily Dependent Responses

arXiv 2203.06046 ↗First posted 11 Mar 2022stat.ML cs.LG math.STcited by 6

Not on the map. Why?

Abstract (arXiv)

This work provides an online learning rule that is universally consistent under processes on (X,Y) pairs, under conditions only on the X process. As a special case, the conditions admit all processes on (X,Y) such that the process on X is stationary. This generalizes past results which required stationarity for the joint process on (X,Y), and additionally required this process to be ergodic. In particular, this means that ergodicity is superfluous for the purpose of universally consistent online learning.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 4 of its 26 references that are in the map. First posted on arXiv 11 Mar 2022.

Builds on

4 of 26 references.

References · 4

  1. 2019Universal Bayes consistency in metric spacescited by 32
  2. 2017Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processescited by 23
  3. 2022Universal Online Learning: an Optimistically Universal Learning Rulecited by 12
  4. 2021Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible?cited by 6

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 2.

6 papers.

  1. 2022Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classescited by 14
  2. 2023Adversarial Rewards in Universal Learning for Contextual Banditscited by 5
  3. 2024Uncertainty quantification in metric spacescited by 3
  4. 2022Contextual Bandits and Optimistically Universal Learningcited by 2
  5. 2025Conformal and kNN Predictive Uncertainty Quantification Algorithms in Metric Spacescited by 2
  6. 2025Variable Selection Methods for Multivariate, Functional, and Complex Biomedical Data in the AI Agecited by 0