arXiv Machine Learning

Error Bounds for Statistical Estimators in BTL Model with Parametric Multivariate Utility Functions

The paper investigates preference elicitation under the Bradley‑Terry‑Luce model, focusing on estimating an unknown partworth vector from pairwise queries that satisfy a joint identifiability condition. It derives minimax lower bounds and shows that the canonical maximum likelihood estimator (MLE) exists, is unique, and achieves near‑optimal error rates once the sample size exceeds a design‑dependent threshold, without requiring compactness constraints or external regularizers. The analysis decomposes the estimation error into a linear stochastic term, a second‑order bias, and a higher‑order remainder, providing a unified non‑asymptotic theory for parametric utility elicitation.

arXiv Statistics ML
Oct 27

Wasserstein-Cram\'er-Rao Theory of Unbiased Estimation

arXiv:2511.07414v2 Announce Type: replace-cross Abstract: The quantity of interest in the classical Cram\'er-Rao theory of unbiased estimation (e.g., the Cram\'er-Rao lower bound, its exact attainmen...

By Nicol\'as Garc\'ia Trillos, Adam Quinn Jaffe, Bodhisattva Sen
arXiv Statistics ML
Nov 9

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

The paper addresses how to allocate a fixed evaluation budget across heterogeneous large language model judges to estimate scores for multiple prompt-response pairs most accurately. It introduces an inverse‑variance weighted estimator (IVWE) and an adaptive algorithm, EST‑IVWE, that uses optimistic variance estimates to approximate the oracle allocation. The authors prove that EST‑IVWE achieves near‑oracle error rates and establish a local minimax lower bound, demonstrating asymptotic instance‑optimality up to logarithmic factors, and validate the method on synthetic data and HelpSteer2 evaluations.

By Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Prouti\`ere, Se-Young Yun
arXiv Statistics ML
Nov 6

Beyond Maximum Likelihood: Variational Inequality Estimation for Generalized Linear Models

The paper introduces a variational inequality (VI) framework for estimating parameters in generalized linear models (GLMs), offering an alternative to the traditional maximum likelihood estimation (MLE). It provides finite‑sample error bounds, asymptotic normality, and convergence guarantees for both fixed‑point and stochastic approximation algorithms, and extends to generalized additive models (GAMs). Numerical experiments show that, within a fixed iteration budget, the VI method achieves comparable or better estimation accuracy and more stable, faster convergence than MLE, especially for GLMs and GAMs with non‑canonical or non‑smooth link functions.

By Linglingzhi Zhu, Jonghyeok Lee, Yao Xie
arXiv Machine Learning
Aug 11

Kernel Methods for Refined Prophet Inequalities

arXiv:2608. 08662v1 Announce Type: cross Abstract: The single-selection prophet inequality is a canonical Bayesian online selection problem in which independent nonnegative values arrive sequentially and the decision-maker must irrevocably select at most one.

By Patrick Loiseau, Mathieu Molina, Vianney Perchet, Sebastian Perez-Salazar, Victor Verdugo
arXiv Machine Learning
Jun 9

Partial Identification under Missing Data Using Weak Shadow Variables from Pretrained Models

arXiv:2602. 16061v2 Announce Type: replace-cross Abstract: Estimating population quantities such as mean outcomes from user feedback is fundamental to platform evaluation and social science, yet feedback is often missing not at random (MNAR): users with stronger opinions are more likely to respond, so standard estimators are biased and the estimand is not identified without additional assumptions.

By Hongyu Chen, David Simchi-Levi, Ruoxuan Xiong
arXiv Machine Learning
Jun 19

Indexed Bellman Information Complexity

arXiv:2606. 11171v2 Announce Type: replace Abstract: We develop indexed Bellman information complexity, a representation-level theory of interactive decision making centered on information indices and reference histories.

By Yunbei Xu