scispace - formally typeset
M

Michalis K. Titsias

Researcher at Athens University of Economics and Business

Publications -  96
Citations -  5467

Michalis K. Titsias is an academic researcher from Athens University of Economics and Business. The author has contributed to research in topics: Gaussian process & Markov chain Monte Carlo. The author has an hindex of 31, co-authored 89 publications receiving 4741 citations. Previous affiliations of Michalis K. Titsias include University of Ioannina & Wellcome Trust Centre for Human Genetics.

Papers
More filters
Proceedings Article

Variational Learning of Inducing Variables in Sparse Gaussian Processes

TL;DR: A variational formulation for sparse approximations that jointly infers the inducing inputs and the kernel hyperparameters by maximizing a lower bound of the true log marginal likelihood.
Proceedings Article

Bayesian Gaussian Process Latent Variable Model

TL;DR: In this article, a variational inference framework for training the Gaussian process latent variable model and thus performing Bayesian nonlinear dimensionality reduction is introduced, which can automatically select the dimensionality of the nonlinear latent space.

Doubly Stochastic Variational Bayes for non-Conjugate Inference (ICML 2014)

TL;DR: A simple and effective variational inference algorithm based on stochastic optimisation that can be widely applied for Bayesian non-conjugate inference in continuous parameter spaces and allows for efficient use of gradient information from the model joint density is proposed.
Proceedings Article

Variational Heteroscedastic Gaussian Process Regression

TL;DR: This work presents a non-standard variational approximation that allows accurate inference in heteroscedastic GPs (i.e., under input-dependent noise conditions) and its effectiveness is illustrated on several synthetic and real datasets of diverse characteristics.