Gaussian process classification using posterior linearisation
This work addresses classification problems in machine learning, but it is incremental as it builds on existing Gaussian process methods.
The paper tackles Gaussian process classification by proposing a posterior linearisation algorithm, which achieves better performance than expectation propagation in experiments, particularly with the noisy threshold likelihood and parallel implementations.
This paper proposes a new algorithm for Gaussian process classification based on posterior linearisation (PL). In PL, a Gaussian approximation to the posterior density is obtained iteratively using the best possible linearisation of the conditional mean of the labels and accounting for the linearisation error. PL has some theoretical advantages over expectation propagation (EP): all calculated covariance matrices are positive definite and there is a local convergence theorem. In experimental data, PL has better performance than EP with the noisy threshold likelihood and the parallel implementation of the algorithms.