Office: Mudd 422
Phone: (212) 854-8024
500 W. 120th St., Suite 1300
New York, NY
|Beta process factor analysis (BPFA) [ matlab code ]
|Information: This is an implementation of the scalable EM version of BPFA,
a Bayesian nonparametric factor analysis model based on the beta
process prior. Batch inference option is also available. This inference
fixes issues with the original variational formulation of the ICML 2009
paper and I think should be used in place of that version.
Paper (code version): S. Sertoglu and J. Paisley. "Scalable Bayesian nonparametric dictionary learning," EUSIPCO 2015.
Paper (original): J. Paisley and L.
Carin. "Nonparametric factor
analysis with beta process priors," ICML 2009.
|Nested hierarchical Dirichlet process (nHDP) [ matlab code ]
A stochastic implementation of the nHDP algorithm for discrete data
(e.g., topic modeling). A batch version of the algorithm can by
obtained by inputing the same data set each iteration and fixing the
step length to one.
Paper: J. Paisley, C. Wang, D. Blei and M. Jordan. "Nested hierarchical Dirichlet processes," IEEE TPAMI, vol. 37, no. 2, pp. 256-270, 2015.
|Markov mixed membership model [ matlab code ] (Author: Aonan Zhang)
|Paper: A. Zhang and J. Paisley. "Markov mixed membership models," ICML 2015.
|Collaborative Kalman filter [ matlab code ] (Author: San Gultekin)
|Paper: S. Gultekin and J. Paisley. "A collaborative Kalman filter for time-evolving dyadic processes," ICDM 2014.
|Gaussian process manifold landmark algorithm [ python code ] (Author: Dawen Liang)
|Paper: D. Liang and J. Paisley. "Landmarking manifolds with Gaussian processes," ICML 2015.
|Scalable Poisson matrix factorization [ python code ] (Author: Dawen Liang)
|Information: This code implements stochastic variational inference for the
Poisson matrix factorization model with gamma priors. The ISMIR version
is the newer one and has some added functionality.
Paper (code version): D. Liang, J.
Paisley and D. Ellis. "Codebook-based scalable music tagging with
Poisson matrix factorization," ISMIR 2014.
Paper (original): J. Paisley, D. Blei and M.I. Jordan. "Bayesian
nonnegative matrix factorization with stochastic variational
inference." Handbook of Mixed Membership Models and Their Applications. Chapman and Hall/CRC Handbooks of Modern Statistical Methods, 2014.
|Discrete infinite logistic normal model [ matlab code ]
|Paper: J. Paisley, C. Wang and D. Blei. "The discrete infinite logistic normal
Analysis, vol. 7, no. 2,
pp. 235-272, 2012.
|BPFA for CS-MRI [ matlab code ] (coming soon)
|Information: This file contains additional Fourier packages used by our code for fast operations in k-space.
Paper: Y. Huang, J. Paisley, Q. Lin, X.
Ding, X. Fu and X.P. Zhang. "Bayesian nonparametric dictionary learning
for compressed sensing MRI," IEEE Transactions on Image Processing, vol. 23, no. 12, pp. 5007-5019, 2014.