Data Reuse in Non-Stationary Learning

Key points

• Recurrence opens the possibility of judiciously reusing past observations to improve algorithm performance.1
• Specifically, we propose a class of anytime algorithms, dubbed Exposure-Capped Reuse (ECR), that combine online change detection, compatibility testing, and "contamination" control.1
• We characterize the regime in which ECR's regret scales with the number of distinct values rather than the number of changes, and derive a novel information-theoretic lower bound that establishes the near-minimax optimality of ECR.1
• This provides rigorous quantification of the statistical "value" of data reuse.1

Sources (1)

• [1]Data Reuse in Non-Stationary Learning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:20 PM

  We consider online learning in non-stationary environments, where the goal is to track an unknown parameter that switches abruptly between a finite set of recurring values.

  Recurrence opens the possibility of judiciously reusing past observations to improve algorithm performance.

Extractive summary: sentences quoted from the sources.