The Performance of the MLE in the Bradley-Terry-Luce Model in ℓ_∞-Loss and under General Graph Topologies

10/20/2021
by   Wanshan Li, et al.
0

The Bradley-Terry-Luce (BTL) model is a popular statistical approach for estimating the global ranking of a collection of items of interest using pairwise comparisons. To ensure accurate ranking, it is essential to obtain precise estimates of the model parameters in the ℓ_∞-loss. The difficulty of this task depends crucially on the topology of the pairwise comparison graph over the given items. However, beyond very few well-studied cases, such as the complete and Erdös-Rényi comparison graphs, little is known about the performance of the maximum likelihood estimator (MLE) of the BTL model parameters in the ℓ_∞-loss under more general graph topologies. In this paper, we derive novel, general upper bounds on the ℓ_∞ estimation error of the BTL MLE that depend explicitly on the algebraic connectivity of the comparison graph, the maximal performance gap across items and the sample complexity. We demonstrate that the derived bounds perform well and in some cases are sharper compared to known results obtained using different loss functions and more restricted assumptions and graph topologies. We further provide minimax lower bounds under ℓ_∞-error that nearly match the upper bounds over a class of sufficiently regular graph topologies. Finally, we study the implications of our bounds for efficient tournament design. We illustrate and discuss our findings through various examples and simulations.

READ FULL TEXT
research
10/21/2021

Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model

Ranking problems based on pairwise comparisons, such as those arising in...
research
09/07/2019

On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons

This paper studies the problem of finding the exact ranking from noisy c...
research
06/21/2014

Minimax-optimal Inference from Partial Rankings

This paper studies the problem of inferring a global preference based on...
research
07/19/2017

Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons

Pairwise comparison data arises in many domains, including tournament ra...
research
04/13/2023

Ranking from Pairwise Comparisons in General Graphs and Graphs with Locality

This technical report studies the problem of ranking from pairwise compa...
research
05/06/2015

Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence

Data in the form of pairwise comparisons arises in many domains, includi...
research
02/20/2021

Generalization bounds for graph convolutional neural networks via Rademacher complexity

This paper aims at studying the sample complexity of graph convolutional...

Please sign up or login with your details

Forgot password? Click here to reset