paper-with-me

홈 › Papers

Aggregating Incomplete and Noisy Rankings

2020-11-02 · Dimitris Fotakis, Alkis Kalavasis, Konstantinos Stavropoulos

We consider the problem of learning the true ordering of a set of alternatives from largely incomplete and noisy rankings. We introduce a natural generalization of both the classical Mallows model of ranking distributions and the extensively studied model of noisy pairwise comparisons. Our selective Mallows model outputs a noisy ranking on any given subset of alternatives, based on an underlying Mallows distribution. Assuming a sequence of subsets where each pair of alternatives appears frequently enough, we obtain strong asymptotically tight upper and lower bounds on the sample complexity of learning the underlying complete ranking and the (identities and the) ranking of the top-k alternatives from selective Mallows rankings. Moreover, building on the work of (Braverman and Mossel, 2009), we show how to efficiently compute the maximum likelihood complete ranking from selective Mallows rankings.

📄 PDF Abstract BibTeX arXiv:2011.00810

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Aggregating Incomplete Rankings

2024-02-26 · Yasunori Okumura

This study considers the method to derive a ranking of alternatives by aggregating the rankings submitted by several individuals who may not evaluate all of them. The collection of subsets of alternatives that individual…

ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities

2024-12-09 · Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu, Vishaal Udandarao 외

Traditional fixed test sets fall short in evaluating open-ended capabilities of foundation models. To address this, we propose ONEBench(OpeN-Ended Benchmarking), a new testing paradigm that consolidates individual evalua…

AllBenchmarking

Label Ranking through Nonparametric Regression

2021-11-04 · Dimitris Fotakis, Alkis Kalavasis, Eleni Psaroudaki

Label Ranking (LR) corresponds to the problem of learning a hypothesis that maps features to rankings over a finite set of labels. We adopt a nonparametric regression approach to LR and obtain theoretical performance gua…

regression

Multiagent Evaluation under Incomplete Information

2019-09-21 · NeurIPS 2019 12 · Mark Rowland, Shayegan Omidshafiei, Karl Tuyls, Julien Perolat 외

This paper investigates the evaluation of learned multiagent strategies in the incomplete information setting, which plays a critical role in ranking and training of agents. Traditionally, researchers have relied on Elo …

Efficient Bayesian Inference from Noisy Pairwise Comparisons

2025-10-10 · Till Aczel, Lucas Theis, Roger Wattenhofer arxiv

Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more reliable but costly and noisy, as participants vary in expertise, attention, and di…

Bayesian Inference