arXiv Machine Learning By Yicheng Li, Huifu Xu

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

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

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