Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2611.02012

Randomized Adaptive Sequential Allocation and the Limits of Bounded Exposure to Inferior Treatments

Sampurna Kundu·Monitirtha Dey·Atanu Biswas
View original source ↗Read source document ↗Export metadata ↓

Abstract

A clinical trial must learn which treatment is superior while sparing its participants from the inferior one. Kundu et al. 2025 recently showed that a purely deterministic rule, which always assigns the treatment with the larger current sample mean, achieves a strong form of this ethical goal. The smaller allocation count stays almost surely finite and has all moments bounded uniformly in the sample size. Deterministic allocation is, however, predictable, and predictability invites selection bias. We ask whether this bounded-exposure phenomenon survives once the deterministic rule is replaced by a smooth randomized one. We show that it does not. Under any fixed non-degenerate symmetric randomization, both treatments are sampled infinitely often, the adaptive sample means are strongly consistent, and the inferior treatment draws a strictly positive limiting allocation proportion. Consequently, the inferior allocation count grows linearly and its moments are unbounded. We then study annealed randomization, in which the randomization scale cools with the accumulated information, and obtain summability and divergence criteria that separate finite, sublinear, and linear exposure. A forced-exploration variant identifies the superior treatment with probability one while keeping the inferior exposure sublinear, and thereby frees the annealed guarantees from any correct-stabilization event. We also treat normalized multi-treatment rules, ties, indifference zones, unequal variances, general response distributions, and local alternatives. Finally, we develop the post-trial asymptotic inference that each exposure regime permits. The results delineate the trade-off between allocation concealment, persistent exploration, and ethical concentration on the superior treatment.

Explore related subjects

math.STstat.MEstat.TH

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Sampurna Kundu, Monitirtha Dey, Atanu Biswas. 2026-11-01. Randomized Adaptive Sequential Allocation and the Limits of Bounded Exposure to Inferior Treatments. https://arxiv.org/abs/2611.02012

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Gaussian Approximation for High-Dimensional Weighted and Two-Sample $U$-statistics with Size-Dependent Kernels

We develop Gaussian approximations for high-dimensional vectors formed by second-order $U$-and $V$-statistics whose kernels depend on sample size. To accommodate weighted and two-sample $U$-and $V$-statistics within a unified framework, we establish our results under independent but not identically distributed (i.n.i.d.) sampling. The resulting theorems apply to a broad range of problems, including estimation in linear regression models with many covariates or many-weak instruments, variance component analysis, smoothed two-sample testing, and inference for separately exchangeable arrays, among others. Our results do not require either component of the Hoeffding decomposition to dominate, thereby covering both non-degenerate and degenerate regimes. In addition, we develop maximal inequalities for high-dimensional $U$-statistics with size-dependent kernels under the i.n.i.d.~setting, in a form that remains sharp across a broad range of applications, which may be of independent interest. Finally, applications to estimation and testing with many weak instrumental variables demonstrate that, our results are sharp enough to recover the corresponding fixed-dimensional rate conditions up to logarithmic factors.

math.ST↗
arXiv2026

Asymmetric conformal prediction with penalized kernel sum-of-squares

Conformal prediction (CP) is a distribution-free method to construct reliable prediction intervals that has gained significant attention in recent years. Despite its success and various proposed extensions, a significant practical feature which has been overlooked in previous research is the potential skewed nature of the noise, or of the residuals when the predictive model exhibits bias. In this work, we leverage recent developments in CP to propose a new asymmetric procedure that bridges the gap between skewed and non-skewed noise distributions, while still maintaining adaptivity of the prediction intervals. We introduce a new statistical learning problem to construct adaptive and asymmetric prediction bands, with a unique feature based on a penalty which promotes symmetry: when its intensity varies, the intervals smoothly change from symmetric to asymmetric ones. This learning problem is based on reproducing kernel Hilbert spaces and the recently introduced kernel sum-of-squares framework. First, we establish representer theorems to make our problem tractable in practice, and derive dual formulations which are essential for scalability to larger datasets. Second, the intensity of the penalty is chosen using a novel data-driven method which automatically identifies the symmetric nature of the noise. We show that consenting to some asymmetry can let the learned prediction bands better adapt to small sample regimes or biased predictive models.

math.ST↗
arXiv2026

The Pivotal Information Criterion

The Bayesian and Akaike information criteria aim at finding a good balance between under- and over-fitting. They are extensively used every day by practitioners. Yet we contend they suffer from at least two afflictions: their penalty parameters $λ=\log n$ and $λ=2$ are too small, leading to many false discoveries, and their inherent (best subset) discrete optimization is infeasible in high dimension. We alleviate these issues with the pivotal information criterion: PIC is defined as a continuous optimization problem, and the PIC penalty parameter $λ$ is selected at the detection boundary (under pure noise). PIC's choice of $λ$ is an upper quantile of a statistic that we prove to be (asymptotically) pivotal, provided the loss function is appropriately transformed. As a result, simulations show a phase transition in the probability of exact support recovery with PIC, a phenomenon studied with no noise in compressed sensing. Applied to real data, for similar predictive performances, PIC selects the least complex model among state-of-the-art learners.

math.ST↗