Research : Papers

This page is last updated in 2014. To see an updated publication page, check out my MLCS page or my Google Scholar page.

Working Papers

• Consistency and Fluctuations for Stochastic Gradient Langevin Dynamics.
  Y. W. Teh, A. Thiery and S. Vollmer.
  [bibtex] [arxiv]

• Bayesian Nonparametric Crowdsourcing.
  P. G. Moreno, Y. W. Teh, F. Perez-Cruz, A. Artes-Rodriguez.
  [bibtex] [arxiv]

• A Marginal Sampler for sigma-Stable Poisson-Kingman Mixture Models.
  M. Lomeli, S. Favaro and Y. W. Teh.
  [bibtex] [arxiv]

• Adaptive Reconfiguration Moves for Dirichlet Mixtures.
  T. Herlau, M. Morup, Y. W. Teh and M. N. Schmidt.
  [bibtex] [arxiv]

• Rediscovery of Good-Turing estimators via Bayesian nonparametrics.
  S. Favaro, B. Nipoti and Y. W. Teh.
  [bibtex] [arxiv]

• Bayesian Nonparametric Modelling of Genetic Variations using Fragmentation-Coagulation Processes.
  Y. W. Teh, L. T. Elliott and C. Blundell.
  [bibtex] [pdf]

2014

• Asynchronous Anytime Sequential Monte Carlo.
  B. Paige, F. Wood, A. Doucet and Y. W. Teh. NIPS 2014.
  [bibtex] [arxiv] [NIPS 2014]

• Mondrian Forests: Efficient Online Random Forests.
  B. Lakshminarayanan, D. M. Roy and Y. W. Teh. NIPS 2014.
  [bibtex] [arxiv] [code] [NIPS 2014]

• Distributed Context-Aware Bayesian Posterior Sampling via Expectation Propagation.
  M. Xu, Y. W. Teh, J. Zhu and B. Zhang. NIPS 2014.
  [bibtex] [NIPS 2014]

• On a Class of sigma-Stable Poisson-Kingman Models and an Effective Marginalized Sampler.
  S. Favaro, M. Lomeli and Y. W. Teh. Statistics and Computing 2014.
  [bibtex] [doi] [springer]

• On the Stick-Breaking Representation of sigma-Stable Poisson-Kingman Models.
  S. Favaro, M. Lomeli, B. Nipoti and Y. W. Teh. Electronic Journal of Statistics 2014.
  [bibtex] [doi] [euclid]

• Bayesian Nonparametric Plackett-Luce Models for the Analysis of Clustered Ranked Data.
  F. Caron, Y. W. Teh and B. T. Murphy. Annals of Applied Statistics 2014.
  [bibtex] [doi] [arxiv]

2013

• Inferring Ground Truth from Multi-annotator Ordinal Data: A Probabilistic Approach.
  B. Lakshminarayanan and Y. W. Teh.
  [bibtex] [arxiv] [code]

• Stochastic Gradient Riemannian Langevin Dynamics on the Probability Simplex.
  S. Patterson and Y. W. Teh. NIPS 2013.
  [bibtex] [pdf] [code]

• Bayesian Hierarchical Community Discovery.
  C. Blundell and Y. W. Teh. NIPS 2013.
  [bibtex] [pdf]

• Learning with Invariances via Linear Functionals on Reproducing Kernel Hilbert Space.
  X. Zhang and W. S. Lee and Y. W. Teh. NIPS 2013.
  [bibtex] [pdf]

• Fast MCMC Sampling for Markov Jump Processes and Extensions.
  V. Rao and Y. W. Teh. JMLR 14:3207-3232, 2013.
  [bibtex] [pdf]

• MCMC for Normalized Random Measure Mixture Models.
  S. Favaro and Y. W. Teh. Statistical Science 28(3):335-359, 2013.
  [bibtex] [pdf] [slides]

• Top-down Particle Filtering for Bayesian Decision Trees.
  B. Lakshminarayanan, D. Roy, Y. W. Teh. ICML 2013.
  [bibtex] [arxiv] [code]

• Dependent Normalized Random Measures.
  C. Chen, V. Rao, W. Buntine, Y. W. Teh. ICML 2013.
  [bibtex] [pdf] [supplementary]

2012

• Actor-Critic Reinforcement Learning with Energy-Based Policies.
  N. Heess D. Silver and Y. W. Teh. Journal of Machine Learning Research Conference and Workshop Proceedings (European Workshop on Reinforcement Learning) 2012.
  [bibtex] [pdf] [EWRL 2012]

• Learning Label Trees for Probabilistic Modelling of Implicit Feedback.
  A. Mnih and Y. W. Teh. NIPS 2012.
  [bibtex] [pdf] [NIPS 2012]

• MCMC for Continuous-Time Discrete-State Systems.
  V. Rao and Y. W. Teh. NIPS 2012.
  [bibtex] [pdf] [supplementary] [NIPS 2012]

• Bayesian Nonparametric Models for Ranked Data.
  F. Caron and Y. W. Teh. NIPS 2012.
  [bibtex] [pdf] [supplementary] [NIPS 2012]

• Scalable Imputation of Genetic Data with a Discrete Fragmentation-Coagulation Process.
  L. T. Elliott and Y. W. Teh. NIPS 2012.
  [bibtex] [pdf] [NIPS 2012]

• Searching for Objects Driven by Context.
  B. Alexe, N. Heess, Y. W. Teh and V. Ferrari. NIPS 2012.
  [bibtex] [pdf] [NIPS 2012]

• A Fast and Simple Algorithm for Training Neural Probabilistic Language Models.
  A. Mnih and Y. W. Teh. ICML 2012.
  [bibtex] [pdf] [poster] [ICML 2012]

2011

• Modelling Genetic Variations using Fragmentation-Coagulation Processes.
  Y. W. Teh, C. Blundell and L. T. Elliott. NIPS 2011.
  [bibtex] [pdf] [slides] [video] [NIPS 2011]

• Gaussian Process Modulated Renewal Processes.
  V. Rao and Y. W. Teh. NIPS 2011.
  [bibtex] [pdf] [supplementary] [slides] [NIPS 2011]

• Fast MCMC sampling for Markov jump processes and continuous time Bayesian networks.
  V. Rao and Y. W. Teh. UAI 2011.
  [bibtex] [pdf] [djvu] [slides] [UAI 2011]

• Bayesian Learning via Stochastic Gradient Langevin Dynamics.
  M. Welling and Y. W. Teh. ICML 2011.
  [bibtex] [pdf] [djvu] [slides] [ICML 2011]

• Mixed Cumulative Distribution Networks.
  R. Silva, C. Blundell and Y. W. Teh. AISTATS 2011.
  [bibtex] [pdf] [djvu] [supplemental] [AISTATS 2011]

• Concave-Convex Adaptive Rejection Sampling.
  D. Gorur and Y.W. Teh. JCGS, 2011.
  [bibtex] [pdf] [djvu] [JCGS]

• The Sequence Memoizer.
  F. Wood, C. Archambeau, J. Gasthaus, L. F. James and Y.W. Teh. CACM, 54(2):91-98, Feb 2011.
  [bibtex] [pdf] [djvu] [slides] [CACM]

• Discovering Non-binary Hierarchical Structures with Bayesian Rose Trees.
  C. Blundell, Y.W. Teh and K.A. Heller. In Mixture Estimation and Applications.
  [bibtex] [pdf] [djvu] [slides] [Workshop] [Wiley] [UAI version]

2010

• Improvements to the Sequence Memoizer.
  J. Gasthaus and Y.W. Teh. NIPS 2010.
  [bibtex] [pdf] [djvu] [supplemental] [slides] [NIPS 2010]

• Bayesian Rose Trees.
  C. Blundell, Y.W. Teh and K.A. Heller. UAI 2010.
  [bibtex] [pdf] [djvu] [slides] [UAI 2010] [Book chapter version]

• Bayesian Nonparametric Models.
  P. Orbanz and Y.W. Teh. Encyclopedia of Machine Learning, to appear. Springer.
  [bibtex] [pdf] [djvu] [Encyclopedia of Machine Learning]

• Dirichlet Processes.
  Y.W. Teh. Encyclopedia of Machine Learning, to appear. Springer.
  [bibtex] [pdf] [djvu] [Encyclopedia of Machine Learning]

• Lossless Compression based on the Sequence Memoizer.
  J. Gasthaus and F. Wood and Y.W. Teh. DCC 2010.
  [bibtex] [pdf] [djvu] [slides] [DCC 2010]

2009

• Indian Buffet Processes with Power-law Behavior.
  Y.W. Teh and D. Gorur. NIPS 2009.
  [bibtex] [pdf] [djvu] [NIPS 2009]

• Spatial Normalized Gamma Processes.
  V. Rao and Y.W. Teh. NIPS 2009.
  [bibtex] [pdf] [djvu] [NIPS 2009]

• Hierarchical Bayesian Nonparametric Models with Applications .
  Y.W. Teh and M.I. Jordan. Bayesian Nonparametrics, 2010. Cambridge University Press.
  [bibtex] [pdf] [djvu] [Cambridge University Press]

• On Smoothing and Inference for Topic Models.
  A. Asuncion, M. Welling, P. Smyth and Y.W. Teh. UAI 2009.
  [bibtex] [pdf] [UAI 2009]

• A Stochastic Memoizer for Sequence Data.
  F. Wood, C. Archambeau, J. Gasthaus, L. F. James and Y.W. Teh. ICML 2009.
  [bibtex] [pdf] [ICML 2009]

• Variational Inference for the Indian Buffet Process.
  F. Doshi, K. T. Miller, J. Van Gael and Y.W. Teh. AISTATS 2009.
  [bibtex] [pdf] [AISTATS 2009]

• Infinite Hierarchical Hidden Markov Models.
  K. Heller, Y.W. Teh and D. Gorur. AISTATS 2009.
  [bibtex] [pdf] [AISTATS 2009]

• A Hierarchical Nonparametric Bayesian Approach to Statistical Language Model Domain Adaptation.
  F. Wood and Y.W. Teh. AISTATS 2009.
  [bibtex] [pdf] [AISTATS 2009]

• Hierarchical Dirichlet Trees for Information Retrieval.
  G.R. Haffari and Y.W. Teh. NAACL-HLT 2009.
  [bibtex] [pdf] [NAACL-HLT 2009]

2008

• The Mondrian Process.
  D.M. Roy and Y.W. Teh. NIPS 2008.
  [bibtex] [pdf] [djvu] [NIPS 2008]

• An Efficient Sequential Monte-Carlo Algorithm for Coalescent Clustering.
  D. Gorur and Y.W. Teh. NIPS 2008.
  [bibtex] [pdf] [djvu] [NIPS 2008]

• The Infinite Factorial Hidden Markov Model.
  J. Van Gael, Y.W. Teh and Z. Ghahramani. NIPS 2008.
  [bibtex] [pdf] [djvu] [NIPS 2008]

• Dependent Dirichlet Process Spike Sorting.
  J. Gasthaus, F. Wood, D. Gorur and Y.W. Teh. NIPS 2008.
  [bibtex] [pdf] [djvu] [NIPS 2008]

• A Mixture Model for the Evolution of Gene Expression in Non-homogeneous Datasets.
  G. Quon, Y.W. Teh, E. Chan, M. Brudno, T. Hughes and Q.D. Morris. NIPS 2008.
  [bibtex] [pdf] [djvu] [NIPS 2008]

• Hybrid Variational/Gibbs Inference in Topic Models.
  M. Welling, Y.W. Teh and B. Kappen UAI 2008.
  [bibtex] [pdf] [djvu] [UAI 2008]

• Beam Sampling for the Infinite Hidden Markov Model.
  J. Van Gael, Y. Saatci, Y.W. Teh and Z. Ghahramani. ICML 2008.
  [bibtex] [pdf] [djvu] [ICML 2008] [code] [presentation]

2007

• Names and Faces.
  T.L. Berg, A.C. Berg, J. Edwards, M. Maire, R. White, Y.W. Teh, E. Learned-Miller, D.A. Forsyth. Submitted.
  [bibtex] [pdf]

• Bayesian Agglomerative Clustering with Coalescents.
  Y.W. Teh, H. Daume III and D.M. Roy. NIPS 2007.
  [bibtex] [pdf] [djvu] [supplemental] [NIPS 2007]

• Collapsed Variational Inference for HDP.
  Y.W. Teh, K. Kurihara and M. Welling. NIPS 2007.
  [bibtex] [pdf] [djvu] [NIPS 2007]

• Cooled and Relaxed Survey Propagation for MRFs.
  H.L. Chieu, W.S. Lee and Y.W. Teh. NIPS 2007.
  [bibtex] [pdf] [djvu] [NIPS 2007] [proof.pdf] [proof.djvu]

• Variational Bayesian Approach to Movie Rating Prediction.
  Y.J. Lim and Y.W. Teh. KDD Cup and Workshop 2007.
  [bibtex] [pdf] [djvu] [KDD Cup 2007]

• Improving Word Sense Disambiguation Using Topic Features.
  J.F. Cai, W.S. Lee and Y.W. Teh. EMNLP 2007.
  [bibtex] [pdf] [djvu] [EMNLP 2007] [SemEval version]

• NUS-ML: Improving Word Sense Disambiguation Using Topic Features.
  J.F. Cai, W.S. Lee and Y.W. Teh. SemEval 2007.
  [bibtex] [pdf] [djvu] [SemEval 2007] [EMNLP version]

• Stick-breaking Construction for the Indian Buffet Process.
  Y.W. Teh, D. Gorur and Z. Ghahramani. AISTATS 2007.
  [bibtex] [pdf] [djvu] [AISTATS 2007]

• Collapsed Variational Dirichlet Process Mixture Models.
  K. Kurihara, M. Welling and Y.W. Teh. IJCAI 2007.
  [bibtex] [pdf] [djvu] [IJCAI 2007]

2006

• Hierarchical Dirichlet Processes.
  Y.W. Teh, M.I. Jordan, M.J. Beal and D.M. Blei. JASA 101(476):1566-1581, 2006.
  [bibtex] [pdf] [djvu] [JASA] [NIPS version] [tech report version]

• A Collapsed Variational Bayesian Inference Algorithm for Latent Dirichlet Allocation.
  Y.W. Teh, D. Newman and M. Welling. NIPS 2006.
  [bibtex] [pdf] [NIPS 2006]

• A Fast Learning Algorithm For Deep Belief Networks.
  G.E. Hinton, S. Osindero and Y.W. Teh. Neural Computation 18(7):1527-1554, 2006.
  [bibtex] [pdf] [djvu] [Neural Computation]

• Unsupervised Discovery of Non-Linear Structure using Contrastive Backpropagation.
  G.E. Hinton, S. Osindero, M. Welling and Y.W. Teh. Cognitive Science 30:4, 2006.
  [bibtex] [pdf] [djvu] [Cognitive Science]

• A Hierarchical Bayesian Language Model based on Pitman-Yor Processes.
  Y.W. Teh. Coling/ACL 2006.
  [bibtex] [pdf] [djvu] [Coling/ACL 2006] [tech report version]

• Bayesian Multi-Population Haplotype Inference via a Hierarchical Dirichlet Process Mixture.
  E.P. Xing, K.-A. Sohn, M.I. Jordan and Y.W. Teh. ICML 2006.
  [bibtex] [pdf] [djvu] [ICML 2006]

• Semi-supervised Learning in Reproducing Kernel Hilbert Spaces Using Local Invariances.
  W.S. Lee, X. Zhang and Y.W. Teh. Technical Report TRB3/06, School of Computing, NUS, 2006.
  [bibtex] [pdf] [djvu] [School of Computing, NUS]

• A Bayesian Interpretation of Interpolated Kneser-Ney.
  Y.W. Teh. Technical Report TRA2/06, School of Computing, NUS, revised 2006.
  [bibtex] [pdf] [djvu] [School of Computing, NUS] [Coling/ACL version]

2005

• Structured Region Graphs: Morphing EP into GBP.
  M. Welling, T. Minka and Y.W. Teh. UAI 2005. Extended version with proofs.
  [bibtex] [pdf] [djvu] [UAI 2005]

• Semiparametric Latent Factor Models.
  Y.W. Teh, M. Seeger and M.I. Jordan. AISTATS 2005.
  [bibtex] [pdf] [djvu] [AISTATS 2005] [tech report version]

• Semiparametric Latent Factor Models.
  M. Seeger, Y.W. Teh and M.I. Jordan. Technical Report, Computer Science, UC Berkeley, 2005.
  [bibtex] [pdf] [djvu] [Computer Science, UC Berkeley] [AISTATS version]

2004

• Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes.
  Y.W. Teh, M.I. Jordan, M.J. Beal and D.M. Blei. NIPS 2004.
  [bibtex] [pdf] [djvu] [NIPS 2004] [JASA version]

• Making Latin Manuscripts Searchable using gHMM's.
  J. Edwards, Y.W. Teh, D.A. Forsyth, M. Maire, R. Bock and G. Vesom. NIPS 2004.
  [bibtex] [pdf] [djvu] [NIPS 2004]

• Faces and Names in the News.
  T. Miller, A.C. Berg, J. Edwards, M. Maire, R. White, Y.W. Teh, E. Learned-Miller, D.A. Forsyth. CVPR 2004.
  [bibtex] [pdf] [djvu] [CVPR 2004]

• Approximate Inference by Markov Chains on Union Spaces.
  M. Welling, M. Rosen-Zvi and Y.W. Teh. ICML 2004.
  [bibtex] [pdf] [djvu] [ICML 2004]

• Hierarchical Dirichlet Processes.
  Y.W. Teh, M.I. Jordan, M.J. Beal and D.M. Blei. Technical Report 653, Statistics, UC Berkeley, 2004.
  [bibtex] [pdf] [djvu] [Statistics, UC Berkeley] [JASA version]

• Linear Response Algorithms for Approximate Inference in Graphical Models.
  M. Welling and Y.W. Teh. Neural Computation 16:197-221, 2004.
  [bibtex] [pdf] [djvu] [Neural Computation] [NIPS version]

2003

• Linear Response Algorithms for Approximate Inference.
  M. Welling and Y.W. Teh. NIPS 2003.
  [bibtex] [pdf] [djvu] [NIPS 2003] [Neural Computation version]

• Energy-Based Models for Sparse Overcomplete Representations.
  Y.W. Teh, M. Welling, S. Osindero and G.E. Hinton. JMLR 4(Dec):1235-1260, 2003.
  [bibtex] [pdf] [djvu] [JMLR]

• Bethe Free Energy and Contrastive Divergence Approximations for Undirected Graphical Models.
  Y.W. Teh. Ph.D. Thesis, 2003. University of Toronto.
  [bibtex] [pdf] [djvu] [Computer Science, Toronto]

• On Improving the Efficiency of the Iterative Proportional Fitting Procedure.
  Y.W. Teh and M. Welling. AISTATS 2003.
  [bibtex] [pdf] [djvu] [AISTATS 2003]

• Approximate Inference in Boltzmann Machines.
  M. Welling and Y.W. Teh. Artificial Intelligence 143(1):19-50, 2003.
  [bibtex] [pdf] [djvu] [Artificial Intelligence] [UAI version]

2002

• Automatic Alignment of Local Representations.
  Y.W. Teh and S. Roweis. NIPS 2002.
  [bibtex] [pdf] [djvu] [NIPS 2002]

• An Alternate Objective Function for Markovian Fields.
  S. Kakade, Y.W. Teh and S. Roweis. ICML 2002.
  [bibtex] [pdf] [djvu] [ICML 2002]

2001

• A New View of ICA.
  G.E. Hinton, M. Welling, Y.W. Teh and S. Osindero. ICA 2001.
  [bibtex] [pdf] [djvu] [ICA 2001] [JMLR version]

• Discovering Multiple Constraints that are Frequently Approximately Satisfied.
  G.E. Hinton and Y.W. Teh. UAI 2001.
  [bibtex] [pdf] [djvu] [UAI 2001]

• The Unified Propagation and Scaling Algorithm.
  Y.W. Teh and M. Welling. NIPS 2001.
  [bibtex] [pdf] [djvu] [NIPS 2001]

• Belief Optimization for Binary Networks: A Stable Alternative to Loopy Belief Propagation.
  M. Welling and Y.W. Teh. UAI 2001.
  [bibtex] [pdf] [djvu] [UAI 2001] [Artificial Intelligence version]

• Passing and Bouncing Messages for Generalized Inference.
  Y.W. Teh and M. Welling. Technical Report 2001-001, Gatsby Unit, UCL.
  [bibtex] [pdf] [djvu] [Gatsby Unit]

2000

• Rate-coded Restricted Boltzmann Machines for Face Recognition.
  Y.W. Teh and G.E. Hinton. NIPS 2000.
  [bibtex] [pdf] [djvu] [NIPS 2000]

• Learning to Parse Images.
  Y.W. Teh, 2000. Master's thesis, University of Toronto.
  [bibtex] [pdf] [djvu] [Computer Science, Toronto] [NIPS version]

1999

• Learning to Parse Images.
  G.E. Hinton, Z. Ghahramani and Y.W. Teh. NIPS 1999.
  [bibtex] [pdf] [djvu] [NIPS 1999] [thesis version]

1998

• Making Forward Chaining Relevant.
  F. Bacchus and Y.W. Teh. AIPS 1998.
  [bibtex] [pdf] [djvu] [AIPS 1998]

Other Reports

• Incremental conservative visibility with general occluders.
  Y.W. Teh and H. Zhang. CSC2522F Project, 1999.
  [pdf] [djvu]

• Wagner's conjecture.
  Y.W. Teh, CSC2410S Project, 1999.
  [pdf] [djvu]

• An attention model and steerable filters.
  Y.W. Teh. CSC2523S Project, 1999.
  [pdf] [djvu]

• Representing coastlines with linear transforms.
  Y.W. Teh. CSC2508S Project, 2000.
  [pdf] [djvu]