Mallows ranking models: maximum likelihood estimate and regeneration

This paper is concerned with various Mallows ranking models. We study the statistical properties of the MLE of Mallows' $\phi$ model. We also make connections of various Mallows ranking models, encompassing recent progress in mathematics. Motivated by the infinite top-$t$ ranking model, we propose an algorithm to select the model size $t$ automatically. The key idea relies on the renewal property of such an infinite random permutation. Our algorithm shows good performance on several data sets.

[1]  J. Marden.  Analyzing and Modeling Rank Data , 1996 .

[2]  Craig Boutilier,et al.  Effective sampling and learning for mallows models with pairwise-preference data , 2014, J. Mach. Learn. Res..

[3]  Ankur Moitra,et al.  Efficiently Learning Mixtures of Mallows Models , 2018, 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS).

[4]  J. Pitman,et al.  Regenerative random permutations of integers , 2017, The Annals of Probability.

[5]  Joachim M. Buhmann,et al.  Cluster analysis of heterogeneous rank data , 2007, ICML '07.

[6]  D. Critchlow.  Metric Methods for Analyzing Partially Ranked Data , 1986 .

[7]  M. Fligner,et al.  Distance Based Ranking Models , 1986 .

[8]  Silvio Lattanzi,et al.  Mallows Models for Top-k Lists , 2018, NeurIPS.

[9]  Raffaello Seri,et al.  Estimation in Discrete Parameter Models , 2012, 1207.5653.

[10]  L. Thurstone.  A law of comparative judgment. , 1994 .

[11]  Valeria Vitelli,et al.  Probabilistic preference learning with the Mallows rank model , 2014, J. Mach. Learn. Res..

[12]  J. A. Lozano,et al.  Sampling and learning the Mallows and Generalized Mallows models under the Cayley distance , 2014 .

[13]  Jeff A. Bilmes,et al.  Consensus ranking under the exponential model , 2007, UAI.

[14]  Craig Boutilier,et al.  Learning Mallows Models with Pairwise Preferences , 2011, ICML.

[15]  Yuxin Chen,et al.  Spectral MLE: Top-K Rank Aggregation from Pairwise Comparisons , 2015, ICML.

[16]  Amir Dembo,et al.  Large Deviations Techniques and Applications , 1998 .

[17]  Absorption sampling and the absorption distribution , 1998 .

[18]  Ashish Kapoor,et al.  Riffled Independence for Efficient Inference with Partial Rankings , 2012, J. Artif. Intell. Res..

[19]  Rudini Menezes Sampaio,et al.  Limits of permutation sequences , 2011, J. Comb. Theory B.

[20]  M. Trick,et al.  Voting schemes for which it can be difficult to tell who won the election , 1989 .

[21]  C. L. Mallows.  NON-NULL RANKING MODELS. I , 1957 .

[22]  R. Luce,et al.  Individual Choice Behavior: A Theoretical Analysis. , 1960 .

[23]  Avrim Blum,et al.  Learning Mixtures of Ranking Models , 2014, NIPS.

[24]  R. Plackett.  The Analysis of Permutations , 1975 .

[25]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .

[26]  P. Diaconis.  Group representations in probability and statistics , 1988 .

[27]  Marina Meila,et al.  Dirichlet Process Mixtures of Generalized Mallows Models , 2010, UAI.

[28]  Carlos Guestrin,et al.  Uncovering the riffled independence structure of ranked data , 2012 .

[29]  William Fithian,et al.  Rank verification for exponential families , 2016, The Annals of Statistics.

[30]  L. Gordon,et al.  Tutorial on large deviations for the binomial distribution , 1989 .

[31]  R. Stanley.  Enumerative Combinatorics: Volume 1 , 2011 .

[32]  A. Pekec,et al.  The repeated insertion model for rankings: Missing link between two subset choice models , 2004 .

[33]  D. Rawlings.  Absorption Processes , 1997 .

[34]  Clyde H. Coombs,et al.  An Empirical Study of Some Election Systems , 1984 .

[35]  Marina Meila,et al.  Tractable Search for Learning Exponential Models of Rankings , 2009, AISTATS.

[36]  Eyke Hüllermeier,et al.  Preference-Based Rank Elicitation using Statistical Models: The Case of Mallows , 2014, ICML.

[37]  J. A. Lozano,et al.  PerMallows: An R Package for Mallows and Generalized Mallows Models , 2016 .

[38]  Yoram Singer,et al.  Learning to Order Things , 1997, NIPS.

[39]  A. Gnedin,et al.  q-exchangeability via quasi-invariance , 2009, 0907.3275.

[40]  Martin J. Wainwright,et al.  Simple, Robust and Optimal Ranking from Pairwise Comparisons , 2015, J. Mach. Learn. Res..

[41]  W. Newey,et al.  Large sample estimation and hypothesis testing , 1986 .

[42]  M. Fligner,et al.  Multistage Ranking Models , 1988 .

[43]  L. Thurstone.  Rank order as a psycho-physical method. , 1931 .

[44]  Joseph S. Verducci,et al.  Probability models on rankings. , 1991 .

[45]  P. Diaconis.  A Generalization of Spectral Analysis with Application to Ranked Data , 1989 .

[46]  D. Hunter.  MM algorithms for generalized Bradley-Terry models , 2003 .

[47]  Yi Mao,et al.  Non-parametric Modeling of Partially Ranked Data , 2007, NIPS.

[48]  Manuela Cattelan,et al.  Models for Paired Comparison Data: A Review with Emphasis on Dependent Data , 2012, 1210.1016.

[49]  R. Duncan Luce,et al.  Individual Choice Behavior: A Theoretical Analysis , 1979 .

[50]  John D. Lafferty,et al.  Cranking: Combining Rankings Using Conditional Probability Models on Permutations , 2002, ICML.

[51]  Marina Meila,et al.  An Exponential Model for Infinite Rankings , 2010, J. Mach. Learn. Res..

[52]  Marina Meila,et al.  Recursive Inversion Models for Permutations , 2014, NIPS.