We compare statistical experiments when observations are inexpensive and can be acquired sequentially until the decision maker chooses to stop. We introduce two orders. Small-cost decision dominance asks which of two equally priced experiments is eventually preferred in every decision problem as the per-observation cost vanishes; large-budget stopping dominance asks which experiment can reproduce every terminal experiment attainable from the other under all sufficiently large expected-sample budgets. Our main result shows that, for generic pairs, the two orders coincide and are both characterized by strict dominance of every pairwise Kullback--Leibler divergence. The key step is a uniform exact-conversion theorem: any finite-output stopping policy based on one experiment can be reproduced exactly using another, with first-order expected-sample requirements determined by pairwise KL rates and a square-root remainder that is uniform over policies.
Interactive decision support systems often require repeated preference judgments, although identifying the best alternative may not justify eliciting all \(n(n-1)/2\) pairwise comparisons. We propose ALEC (Adaptive Lexicographic Elicitation of Comparisons), which re-ranks the alternatives after each judgment and asks t...
This paper considers the Bayesian top-$k$ identification problem, wherein a decision maker is tasked with selecting $k$ items from a pool of items of unknown quality. To assess the items, the decision maker adaptively allocates a fixed sampling budget, where each sample of an item yields a noisy observation of its qual...
We study parameter estimation when each sample from a continuous parametric distribution is accompanied by a binary quality label governed by the same unknown parameter. By imposing hard feasibility constraints, deterministic labels can accelerate estimation from the classical $n^{-1/2}$ rate of smooth quality-aware M-...
We study ranking models by population-average utility from pairwise comparisons when preferences vary across users and tasks. Prior work shows that a single comparison per user can be insufficient to identify the alternative with the highest average utility, even with arbitrarily many users (Golz et al., 2025). We inve...
Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive. Decoding-time policy composition allows these trade-offs to be adjusted by combining reward-specific policies at inference time. This composition targets a weighted pr...
Alexey Kurennoy, R. Yarullin, Fergal Reid· 0 citations
What information is needed to turn a natural-gradient direction into a useful finite update? Under a population Kullback-Leibler (KL) budget, we call a step useful if it is feasible and loses at most a fraction $\varepsilon$ of the best feasible gain along the direction. We construct a four-state exponential family who...
Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.