Active Online Learning with Hidden Shifting Domains

Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations


Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. Motivated by these two challenges, we propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in settings where the data streams are from a mixture of hidden domains. For online linear regression with oblivious adversaries, we provide a tight tradeoff that depends on the durations and dimensionalities of the hidden domains. Our algorithm can adaptively deal with interleaving spans of inputs from different domains. We also generalize our results to non-linear regression for hypothesis classes with bounded eluder dimension and adaptive adversaries. Experiments on synthetic and realistic datasets demonstrate that our algorithm achieves lower regret than uniform queries and greedy queries with equal labeling budget.

Original languageEnglish (US)
Pages (from-to)2053-2061
Number of pages9
JournalProceedings of Machine Learning Research
StatePublished - 2021
Event24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021 - Virtual, Online, United States
Duration: Apr 13 2021Apr 15 2021

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Active Online Learning with Hidden Shifting Domains'. Together they form a unique fingerprint.

Cite this