[2207.00076] Efficient computation of rankings from pairwise comparisons
We study the ranking of individuals, teams, or objects, based on pairwise comparisons between them, using the Bradley-Terry model. Estimates of rankings within this model are commonly made using a simple iterative algo…
Efficient computation of rankings from pairwise comparisons \name M. E. J. Newman \addr Center for the Study of Complex Systems University of Michigan Ann Arbor, MI 48109, USA Abstract We study the ranking of individuals, teams, or objects, based on pairwise comparisons between them, using the Bradley-Terry model. Estimates of rankings within this model are commonly made using a simple iterative algorithm first introduced by Zermelo almost a century ago. Here we describe an alternative and similarly simple iteration that provably returns identical results but does so much faster—over a hundred
Explore this link on the map →related reading
- Bradley–Terry model - Wikipediaen.wikipedia.org
- How Not To Sort By Average Rating – Evan Millerevanmiller.org
- Resorting Media Ratings · Gwern.netgwern.net
- Prompt-to-Leaderboardarxiv.org
- Elo rating system - Wikipediaen.wikipedia.org
- German tank problem - Wikipediaen.wikipedia.org
- Gregory Gundersengregorygundersen.com
- Papers · Nikhil Garggargnikhil.com
- Okapi BM25 - Wikipediaen.wikipedia.org
- AlgZoo: uninterpreted models with fewer than 1,500 parameters — LessWronglesswrong.com
- Bits per Spike as a Betting Game · neurostatsblogneurostatsblog.github.io
- Probabilistic Relevance Frameworkstaff.city.ac.uk