acceptodds
Desk rejected at ICLR 2027

Only Learn What Changes the Decision: Exact Quotient Geometry for Active Acquisition

Desk rejected at ICLR 2027, so left out of the paper lists and the map.

Abstract

Active learning for decision making often estimates more information than is actually needed: it may try to recover a latent parameter even when the final decision depends only on a few observable directions. We study when and how this unnecessary identification can be avoided. Our key insight is to quotient out parameter directions that cannot affect any decision comparison, yielding a decision-observability quotient that contains exactly the information needed for decision making. We show that this reduction is valid if and only if the query space spans all decision-relevant differences, and that under this condition it preserves regret, acceptable answers, and the information-theoretic complexity of the problem. For Gaussian observations, we characterize the exact fixed-confidence sample complexity through a quotient characteristic time and give a practical adaptive algorithm that attains this rate under explicit regularity conditions. We further show that identifying the full parameter can be substantially more expensive: on an explicit family, coordinate-wise identification requires exactly times the characteristic time of decision identification, with stopping-time ratios between and under the self-normalized ellipsoid boundary. Experiments reveal a stark practical gap. On synthetic instances, stopping-time ratios follow the predicted -to- separation, while on 18 public rating panels the coordinate-wise test fails to stop in all runs. On the same runs and confidence events, the quotient test stops times and makes no incorrect recommendation on held-out raters.

Primary area:
learning theory
Keywords:
Decision-Focused Acquisition, Decision Observability, Observable Quotient, Fixed-Confidence Identification

Related papers

Discussion (0)

Sign in to comment.