LGMLJan 31, 2025

DAL: A Practical Prior-Free Black-Box Framework for Non-Stationary Bandits

arXiv:2501.19401v4h-index: 58
Originality Incremental advance
AI Analysis

This provides a practical solution for adaptive decision-making in dynamic environments, though it is incremental as it builds on existing stationary bandit algorithms.

The paper tackles the problem of non-stationary bandits without prior knowledge by introducing the Detection Augmented Learning (DAL) framework, which consistently surpasses current state-of-the-art methods across diverse scenarios, including synthetic benchmarks and real-world datasets.

We introduce a practical, black-box framework termed Detection Augmented Learning (DAL) for the problem of non-stationary bandits without prior knowledge of the underlying non-stationarity. DAL accepts any stationary bandit algorithm as input and augments it with a change detector, enabling applicability to all common bandit variants. Extensive experimentation demonstrates that DAL consistently surpasses current state-of-the-art methods across diverse non-stationary scenarios, including synthetic benchmarks and real-world datasets, underscoring its versatility and scalability. We provide theoretical insights into DAL's strong empirical performance, complemented by thorough experimental validation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes