Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty

• URL: http://arxiv.org/abs/2606.17426v1
• Date: Tue, 16 Jun 2026 02:19:01 GMT
• Title: Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty
• Abstract summary: We consider the concentration properties of functions of infinitely exchangeable random variables.<n>For zero-sum linear contrasts, such as the difference between a subsample mean and a full population mean, the latent mixture term cancels exactly.<n>This cancellation yields a tight, mixture-free Hoeffding-type bound that provides a direct de Finetti mechanism for the infinite-extendibility limit of recent finite-exchangeable concentration results.
• Score: 9.998078491879145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the concentration properties of functions of infinitely exchangeable random variables. By conditioning on the de Finetti directing measure, we show that the deviation of any function with bounded-difference constants $c_1, \dots, c_n$ decomposes into a conditional sampling fluctuation and a latent mixture fluctuation. When this latent mixture is $σ_{\mathrm{mix}}^2$-subgaussian, we establish a concentration inequality with an effective variance proxy of $\frac{1}{4}\sum_i c_i^2 + σ_{\mathrm{mix}}^2$. Crucially, we demonstrate that for zero-sum linear contrasts, such as the difference between a subsample mean and a full population mean, the latent mixture term cancels exactly. This cancellation yields a tight, mixture-free Hoeffding-type bound that provides a direct de Finetti mechanism for the infinite-extendibility limit of recent finite-exchangeable concentration results. We apply this framework to quantify uncertainty in composite AI benchmarks, such as MMLU, where question items naturally exhibit exchangeable dependence across domains. Our results provide both a domain-stratified hierarchical model for bounding the uncertainty of accuracy scores, and a distribution-free, cost-saving statistical guarantee for accurately estimating full benchmark scores from random subsets.

Related papers

• Robust Chance-Constrained Optimization using a Continuous Parameter Space Wasserstein-2 Ambiguity Set of Gaussian Mixtures [0.0]
  We study distributionally robust linear chance-constrained problems in which uncertainty is modeled by a Gaussian mixture model (GMM)<n>We develop an adaptive cutting-surface algorithm, which endogenously determines the locations of mixture components receiving mass.<n>A case study using the electric-vehicle charging-station energy-allocation problem demonstrates the framework's practical value.
  arXiv  Detail & Related papers  (2026-07-19T01:10:05Z)
• Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation [55.47411235954028]
  We recast imputation under missing completely at random as density estimation from masked observations.<n>We obtain a convex empirical risk problem with closed form marginals, solvable by a Newton interior point method.<n>The resulting PSD Impute model yields both single and multiple imputations from the same fitted density.
  arXiv  Detail & Related papers  (2026-07-08T15:51:05Z)
• Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions [0.0]
  In genomics experiments, exchangeability often holds only within subsets of interventions that leave a target variable "unaffected"<n>Our contributions are: (i) a contamination-robust conformal coverage theorem that quantifies how misclassification of "unaffected" calibration examples degrades coverage via an explicit function $g(,n)$ of the contamination fraction and calibration set size; and (ii) a task-driven partial causal learning formulation that estimates only the binary descendant indicators $Z_a,i=mathbf1iinmathrmdesc(a)$ needed
  arXiv  Detail & Related papers  (2026-03-02T18:58:22Z)
• Unified Unbiased Variance Estimation for MMD: Robust Finite-Sample Performance with Imbalanced Data and Exact Acceleration under Null and Alternative Hypotheses [0.0]
  The maximum mean discrepancy (MMD) is a kernel-based nonparametric statistic for two-sample testing.<n>We study the variance of the MMD statistic through its U-statistic representation and Hoeffding decomposition.
  arXiv  Detail & Related papers  (2026-01-20T11:41:32Z)
• Divergence-Minimization for Latent-Structure Models: Monotone Operators, Contraction Guarantees, and Robust Inference [5.373905622325275]
  We develop a divergence-minimization (DM) framework for robust and efficient inference in latent-mixture models.<n>By optimizing a residual-adjusted divergence, the DM approach recovers EM as a special case and yields robust alternatives.
  arXiv  Detail & Related papers  (2025-11-22T08:25:29Z)
• Online Covariance Estimation in Nonsmooth Stochastic Approximation [14.818683408659764]
  We consider applying approximation (SA) methods to solve nonsmooth variational inclusion problems.<n>Our convergence construction establish the best-known for statistical estimation methods.
  arXiv  Detail & Related papers  (2025-02-07T20:16:51Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery [47.36895591886043]
  We investigate heteroscedastic symmetric noise models (HSNMs)<n>We introduce a novel criterion for identifying HSNMs based on the skewness of the score (i.e., the gradient of the log density) of the data distribution.<n>We propose SkewScore, an algorithm that handles heteroscedastic noise without requiring the extraction of external noise.
  arXiv  Detail & Related papers  (2024-10-08T22:28:30Z)
• Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes [44.974100402600165]
  We study the evaluation of a policy best-parametric and worst-case perturbations to a decision process (MDP) We use transition observations from the original MDP, whether they are generated under the same or a different policy. Our estimator is also estimated statistical inference using Wald confidence intervals.
  arXiv  Detail & Related papers  (2024-03-29T18:11:49Z)
• TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression [109.69084997173196]
  Deepscedastic regression involves jointly optimizing the mean and covariance of the predicted distribution using the negative log-likelihood. Recent works show that this may result in sub-optimal convergence due to the challenges associated with covariance estimation. We study two questions: (1) Does the predicted covariance truly capture the randomness of the predicted mean? Our results show that not only does TIC accurately learn the covariance, it additionally facilitates an improved convergence of the negative log-likelihood.
  arXiv  Detail & Related papers  (2023-10-29T09:54:03Z)
• Sparsified Simultaneous Confidence Intervals for High-Dimensional Linear Models [4.675899216825188]
  We propose a notion of simultaneous confidence intervals called the sparsified simultaneous confidence intervals.<n>Our intervals are sparse in the sense that some of the intervals' upper and lower bounds are shrunken to zero.<n>The proposed method can be coupled with various selection procedures, making it ideal for comparing their uncertainty.
  arXiv  Detail & Related papers  (2023-07-14T18:37:57Z)
• Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations [44.71254888821376]
  We provide the first type-I-error and expected-rejection-time guarantees under general non-data generating processes. We show how to apply our results to inference on parameters defined by estimating equations, such as average treatment effects.
  arXiv  Detail & Related papers  (2022-12-29T18:37:08Z)
• A Unified Joint Maximum Mean Discrepancy for Domain Adaptation [73.44809425486767]
  This paper theoretically derives a unified form of JMMD that is easy to optimize. From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence that benefits to classification. We propose a novel MMD matrix to promote the dependence, and devise a novel label kernel that is robust to label distribution shift.
  arXiv  Detail & Related papers  (2021-01-25T09:46:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.