Timezone: »

Heterogeneous Multi-output Gaussian Process Prediction
Pablo Moreno-Muñoz · Antonio Artés · Mauricio Álvarez

Wed Dec 05 01:50 PM -- 01:55 PM (PST) @ Room 220 E

We present a novel extension of multi-output Gaussian processes for handling heterogeneous outputs. We assume that each output has its own likelihood function and use a vector-valued Gaussian process prior to jointly model the parameters in all likelihoods as latent functions. Our multi-output Gaussian process uses a covariance function with a linear model of coregionalisation form. Assuming conditional independence across the underlying latent functions together with an inducing variable framework, we are able to obtain tractable variational bounds amenable to stochastic variational inference. We illustrate the performance of the model on synthetic data and two real datasets: a human behavioral study and a demographic high-dimensional dataset.

Author Information

Pablo Moreno-Muñoz (Universidad Carlos III de Madrid)
Antonio Artés (Universidad Carlos III de Madrid)
Mauricio Álvarez (University of Sheffield)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors