arXiv:2607.06879v1 Announce Type: new Abstract: Best-arm identification is a canonical model for data-driven decision-making, but in many applications each reward observation is costly. Motivated by the growing availability of cheap predictions from machine learning and large language models, we study fixed-confidence best-arm identification in which each costly reward pull is paired with a cheap but correlated proxy score. The marginal mean of the proxy can be estimated offline and is treated as known, whereas its correlation $\rho$ with the reward, which governs how much the proxy helps, is
The proliferation of machine learning and large language models provides cheap prediction capabilities, making the integration of proxy scores into decision-making more feasible and impactful.
This development improves data efficiency and cost-effectiveness in 'best-arm identification' problems, accelerating research and application in areas where data acquisition is expensive.
Decision-making processes in costly observation scenarios can now leverage easily accessible, correlated proxy scores, potentially lowering the barrier to entry for complex data-driven tasks.
- · AI/ML researchers
- · High-cost data industries (e.g., drug discovery, materials science)
- · Cloud providers offering ML/LLM services
- · Traditional, data-intensive experimental methods
- · Organizations slow to adopt advanced AI proxies
Reduced cost and time for identifying optimal strategies in various applications.
Increased adoption of AI-driven decision-making in sectors previously constrained by data acquisition costs.
Acceleration of scientific discovery and industrial optimization due to more efficient experimentation.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG