Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist

Niclas Boehmer, Piotr Faliszewski, Sonja Kraiczy
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2689-2711, 2023.

Abstract

The Mallows model is a popular distribution for ranked data. We empirically and theoretically analyze how the properties of rankings sampled from the Mallows model change when increasing the number of alternatives. We find that real-world data behaves differently from the Mallows model, yet is in line with its recent variant proposed by Boehmer et al. [IJCAI ’21]. As part of our study, we issue several warnings about using the classic Mallows model. For instance, we find that one should be extremely careful when using the Mallows model to generate data for experiments with a varying number of alternatives, as observed trends in such experiments might be due to the changing nature of the generated data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-boehmer23b, title = {Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist}, author = {Boehmer, Niclas and Faliszewski, Piotr and Kraiczy, Sonja}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {2689--2711}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/boehmer23b/boehmer23b.pdf}, url = {https://proceedings.mlr.press/v202/boehmer23b.html}, abstract = {The Mallows model is a popular distribution for ranked data. We empirically and theoretically analyze how the properties of rankings sampled from the Mallows model change when increasing the number of alternatives. We find that real-world data behaves differently from the Mallows model, yet is in line with its recent variant proposed by Boehmer et al. [IJCAI ’21]. As part of our study, we issue several warnings about using the classic Mallows model. For instance, we find that one should be extremely careful when using the Mallows model to generate data for experiments with a varying number of alternatives, as observed trends in such experiments might be due to the changing nature of the generated data.} }
Endnote
%0 Conference Paper %T Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist %A Niclas Boehmer %A Piotr Faliszewski %A Sonja Kraiczy %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-boehmer23b %I PMLR %P 2689--2711 %U https://proceedings.mlr.press/v202/boehmer23b.html %V 202 %X The Mallows model is a popular distribution for ranked data. We empirically and theoretically analyze how the properties of rankings sampled from the Mallows model change when increasing the number of alternatives. We find that real-world data behaves differently from the Mallows model, yet is in line with its recent variant proposed by Boehmer et al. [IJCAI ’21]. As part of our study, we issue several warnings about using the classic Mallows model. For instance, we find that one should be extremely careful when using the Mallows model to generate data for experiments with a varying number of alternatives, as observed trends in such experiments might be due to the changing nature of the generated data.
APA
Boehmer, N., Faliszewski, P. & Kraiczy, S.. (2023). Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:2689-2711 Available from https://proceedings.mlr.press/v202/boehmer23b.html.

Related Material