MLLGMay 11, 2025

Constrained Online Decision-Making: A Unified Framework

MIT
arXiv:2505.07101v34 citationsh-index: 17
Originality Incremental advance
AI Analysis

This work provides a principled foundation for constrained online decision-making, addressing problems like adaptive experimental design and personalized recommendation with constraints, though it is incremental in extending existing concepts to a broader framework.

The paper tackles the problem of sequential decision-making with stage-wise feasibility constraints across various applications, proposing a unified algorithmic framework that uses upper counterfactual confidence bounds and a generalized eluder dimension to achieve strong theoretical guarantees with practical efficiency.

Contextual online decision-making problems with constraints appear in a wide range of real-world applications, such as adaptive experimental design under safety constraints, personalized recommendation with resource limits, and dynamic pricing under fairness requirements. In this paper, we investigate a general formulation of sequential decision-making with stage-wise feasibility constraints, where at each round, the learner must select an action based on observed context while ensuring that a problem-specific feasibility criterion is satisfied. We propose a unified algorithmic framework that captures many existing constrained learning problems, including constrained bandits, active learning with label budgets, online hypothesis testing with Type I error control, and model calibration. Central to our approach is the concept of upper counterfactual confidence bounds, which enables the design of practically efficient online algorithms with strong theoretical guarantees using any offline conditional density estimation oracle. To handle feasibility constraints in complex environments, we introduce a generalized notion of the eluder dimension, extending it from the classical setting based on square loss to a broader class of metric-like probability divergences. This allows us to capture the complexity of various density function classes and characterize the utility regret incurred due to feasibility constraint uncertainty. Our result offers a principled foundation for constrained sequential decision-making in both theory and practice.

Foundations

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

Your Notes