Marina Meila


Handbook of Cluster Analysis with Christian Hennig, Fionn Murtagh and Roberto Rocci


"Manifold Learning: what, How and Why", with Hanyu Zhang (to appear) in Annual Reviews of Statistics and Its Application, Volume 11, 2024.

"The consistency of Dictionary Based Manifold Learning", with Samson Koelle, Hanyu Zhang, and Vlad Murad, AISTATS 2024 (arXiv version here).

"Manifold Coordinates with Physical Meaning", with Samson Koelle, Hanyu Zhang, and Yu-Chia Chen, Journal of Machine Learning Research, 2022. (arXiv:1811.11891) and slides

"The decomposition of the higher-order homology embedding constructed from the k-Laplacian", with Yu-Chia Chen, NeurIPS 2021 (Oral)

"Tangent space least adaptive clustering", with Samson Koelle and James Buenfil, ICML 2021 Workshop on Unsupervised Reinforcement Learning

"Selecting the independent coordinates of manifolds with large aspect ratios", with Yu-Chia Chen, arXiv:1907.01651, NeurIPS 2019

"A regression approach for explaining manifold embedding coordinates", with Samson Koelle and Hanyu Zhang, arXiv:1811.11891, 2018

"Improved graph Laplacian via geometric self-consistency" with Dominique Perrault-Joncas and James McQueen NIPS 2017 slides

"Near isometry by Riemannian Relaxation" (and supplement) with James McQueen and Dominique Perrault-Joncas, NIPS 2016 slides

See how Riemannian Relaxation recovers the shape of a squished sphere (avi) (mov)

"megaman: Manifold Learning with Millions of points" with James McQueen, Marina Meila, Jacob VanderPlas, Zhongyue Zhang, and JMLR short version ""

"Non-linear dimensionality reduction: Riemannian metric estimation and the problem of geometric discovery" with Dominique Perrault-Joncas, (submitted) 2013 slides

"Directed Graph Embedding: an Algorithm based onContinuous Limits of Laplacian-type Operators" with Dominique Perrault-Joncas, NIPS 2011

"Manifold Learning for Real Data" tutorial lectures at the Fields Institute, 2022
Slides for Manifold Learning in the age of Big Data the SPPEXA Annual Plenary Meeting, 2019
Slides for Geometrically faithful non-linear dimension reduction (Is Manifold Learning for toy data only?) at the UC Davis Statistics Symposium, 2016


"Good (K-means) clusterings are unique (up to small perturbations)", Journal of Multivariate Analysis, 2018

"How to tell when a clustering is (approximately) correct using convex relaxations", NeurIPS 2018

"Spectral clustering", an introduction for the 2010's, published in this book

"How the initialization affects the stability of the k-means algorithm", with Sebastien Bubeck and Ulrike von Luxburg, ESAIM: Probability and Statistics 16, 436-452, 2012

"Local equivalences of distances between clusterings - A geometric perspective" Machine Learning Journal, 2011

"Clustering by weighted cuts in directed graphs" with William Pentney, presented at the 2007 SIAM Conference on Data Mining SDM 2007

"The uniqueness of a good clustering for K-means", presented at ICML 2006
An expanded and improved version

"Comparing clusterings -- an information based distance", Journal of Multivariate Analysis, 98, pp 873-895, 2007.

"Comparing subspace clusterings", with Anne Patrikainen, IEEE Transactions on Knowledge and Data Engineering (TKDE) 18(7),902-916

"Spectral clustering of biological sequence data", with William Pentney, AAAI, 2005

"Comparing clusterings -- an axiomatic view". Presented at ICML 2005.

"Unsupervised spectral learning", with Susan Shortreed, UAI 2005.

"Spectral clustering for Microsoft Netscan data", UW CSE-05-06-05 Technical report and CSSS paper no. 49, with Anne Patrikainen

"Regularized spectral learning", UW Statistics Technical Report 465, with Susan Shortreed and Liang Xu. Presented at AISTATS 2005

"Clustering by Intersection-Merging", UW Statistics Technical Report 451, with Qunhua Li

"A comparison of spectral clustering algorithms", UW CSE Technical report 03-05-01, with Deepak Verma

"Multiway cuts and spectral clustering" with Liang Xu (submitted)

"Comparing clusterings" UW Statistics Technical Report 418 and COLT 03 (pdf)

"The multicut lemma" UW Statistics Technical Report 417

"A random walks view of spectral segmentation" Meila, M., Shi J., AISTATS 2001

"An Experimental Comparison of Several Clustering and Initialization Methods" Meila, M., Heckerman D., Microsoft Research Technical report MSR-TR-98-06. , UAI 1998 and Machine Learning Journal, 42:9--42, 2000.


"Measuring the robustness of graph properties", with Yali Wan, arXiv:1901.09661, 2018.

"Graph clustering: block models and model free results" with Yali Wan , NIPS 2016 (to appear)

"Benchmarking recovery theorems for the Degree Corrected Stochastic Block Model" with Yali Wan, ISAIM 2016

"A class of network models recoverable by spectral clustering" with Yali Wan, NIPS 2015


"Recursive Inversion Models for Permutations" with Chris Meek, NIPS 2014 (slides)

"Consensus ranking with signed permutations" with Raman Arora, AISTATS 2013

"Experiments with Kemeny ranking: what works when? with Alnur Ali, Mathematical Social Sciences 64,28-40, 2012

"Preferences in college applications -- a non-parametric Bayesian analysis of top-10 rankings" Alnur Ali, Marina Meila, Brendan Murphy, Harr Chen, NIPS Workshop on Computational Social Science and the Wisdom of Crowds, 2010 (slides)

"Dirichlet Process Mixtures of Generalized Mallows Models" Marina Meila and Harr Chen, UAI 2010, Catalina Island, CA.

"An exponential family model over infinite rankings by Marina Meila and Le Bao, Journal of Machine Learning Research, 10:3481--3518, 2010.

"Estimation and Clustering with Infinite Rankings" by Marina Meila and Le Bao, UAI 2008, Helsinki, Finland, and UW Statistics TR 529

"Clustering permutations by Exponential Blurring Mean-Shift", by Le Bao and Marina Meila, UW Statistics TR 524, 2007

"Consensus ranking under the exponential model", Marina Meila, Kapil Phadnis, Arthur Patterson and Jeff Bilmes, UAI 2007, Vancouver, BC and UW Statistics TR 515

"Intransitivity in classification and choice", with Jeff Bilmes, UWEETR-2006-0021


"Gravimetric inversion by compressed sensing" Marina Meila, Caren Marzban, Ulvi Yurtsever, IGARSS 2008

"Model free gravimetric inversion" Hoyt Koepke, Marina Meila IGARSS 2009


"Learning Bayesian Network Structure using LP Relaxations" Tommi Jaakkola, David Sontag, Amir Globerson, Marina Meila; AISTATS 2010

"Tractable Bayesian Learning of Tree Belief Networks" by M. Meila and T. Jaakkola Statistics and Computing, 26, pp 76-92, 2006 (or UAI 2000 version) (presentation)

"An Accelerated Chow and Liu Algorithm: Fitting Tree Distributions to High-Dimensional Sparse Data" by Marina Meila, AI Memo 1652, CBCL Paper 169. (presented at ICML-99)The ICML version - condensed but more readable

"Learning with Mixtures of Trees" Marina Meila, Michael I. Jordan; Journal of Machine Learning Research, 1(Oct):1-48, 2000.

"A Domain Partitioning Approach to Structure Learning for Graphical Models" by Meila, M., Jordan, M. I.; now part of my thesis.

"Triangulation by continuous embedding" by Meila, M., Jordan, M. I., AI Memo 1605, CBCL Paper 146. It subsumes "An Objective function for belief net triangulation" presented at AISTATS-97 and "Triangulation by continuous embedding" by Meila, M., Jordan, M. I. in Advances in Neural Information Processing Systems 9, M. C. Mozer, M. I. Jordan, T. Petsche (eds.), MIT Press, 1997.


"Data centering in feature space" UW Statistics Technical Report 420, and short version presented at AISTATS 2003

"Intransitive likelihood ratio classifiers" by Jeff Bilmes, Gang Ji and Marina Meila, NIPS*2001

"Maximum Entropy Discrimination" AI Memo 1668, by Jaakkola, T., Meila, M., Jebara, T., NIPS*1999 (see also the presentation)


"Discriminating deformable shape classes" by S. Ruiz-Correa, L. G. Shapiro, M. Meila, G. Berson, presented at NIPS 2003.

"A new paradigm for recognizing 3-D object shapes from range data," by S. Ruiz-Correa, L. G. Shapiro, M. Meila, ICCV 2003, and a long version with more experiments by S. Ruiz-Correa, L. G. Shapiro, M. Meila, J. Cole, G. Berson, S. Capell, UW Technical Report, 2003.

"A new signature-based method for efficient 3-D object recognition" by Salvador Ruiz-Correa, Linda Shapiro and Marina Meila, CVPR 2000.

"A random walks view of spectral segmentation" Meila, M., Shi J., AISTATS 2001

"Learning segmentation by random walks" Meila, M., Shi J., NIPS 2000.


"IkB, NF-kB Regulation Model: Simulation Analysis of Small Number of Molecules," by Anamika Sarkar, Marina Meila and Bob Franza, EURASIP Journal on Bioinformatics and Systems Biology, vol. 2007, Article ID 25250, 2007.


"Real-time particle filters", Technical Report UW-CSE-02-07-01, with Cody Kwok and Dieter Fox, NIPS 2002 and IEEE Special Issue on Real-Time state estimation, 2004.


"Markov Mixtures of Experts" by Meila, M., Jordan, M. I., in R. Murray-Smith and T. A. Johanssen (eds.) 'Multiple Model Approaches to Nonlinear Modelling and Control', Taylor and Francis, 1996.

"Learning fine motion by Markov mixtures of experts" by Meila, M., Jordan, M. I., in Advances in Neural Information Processing Systems 8, D. Touretzky, M. C. Mozer and M. Hasselmo (eds.), MIT Press, 1996 and its extended version Meila, M., Jordan, M. I. "Learning fine motion by Markov mixtures of experts" AI Memo 1567, CBCL Paper 133

Learning the parameters of HMMs with auxilliary input by Meila, M. and Jordan, M. I. (1994) MIT Computational Cognitive Science Tech. Report 9401


"Learning with mixtures of trees", MIT Electrical Engineering and Computer Science, 1999