Probabilistic Non-negative Tensor Factorisation using Markov Chain Monte Carlo
Mikkel Schmidt and Shakir Mohamed
In: EUSIPCO 2009, 24 - 28 August 2009, Glasgow, Scotland.
We present a probabilistic model for learning non-negative tensor factorizations (NTF), in which the tensor factors are latent variables associated with each data dimension. The non-negativity constraint for the latent factors is handled by choosing priors with support on the non-negative numbers. Two Bayesian inference procedures based on Markov chain Monte Carlo sampling are described: Gibbs sampling and Hamiltonian Markov chain Monte Carlo. We evaluate the model on two food science data sets, and show that the probabilistic NTF model leads to better predictions and avoids overfitting compared to existing NTF approaches.
|EPrint Type:||Conference or Workshop Item (Talk)|
|Additional Information:||Appeared in the special session on "Non-negative Matrix and Tensor Factorisations: Statistical Methods and Applications".|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Learning/Statistics & Optimisation|
Theory & Algorithms
|Deposited By:||Shakir Mohamed|
|Deposited On:||21 January 2010|