86 citations · 512 across the 43 of their papers we have counts for
22 papers · 1 filter
Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited
Thang D. Bui, Michalis K. Titsias
Inducing-point-based sparse variational Gaussian processes have become the standard workhorse for scaling up GP models. Recent advances show that these methods can be improved by i…
Gaussian Invariant Markov Chain Monte Carlo
Michalis K. Titsias, Angelos Alexopoulos, Siran Liu +1
We develop sampling methods, which consist of Gaussian invariant versions of random walk Metropolis (RWM), Metropolis adjusted Langevin algorithm (MALA) and second order Hessian or…
Optimal Preconditioning and Fisher Adaptive Langevin Sampling
Michalis K. Titsias
We define an optimal preconditioning for the Langevin diffusion by analytically optimizing the expected squared jumped distance. This yields as the optimal preconditioning an inver…
Gradient Estimation with Discrete Stein Operators
Jiaxin Shi, Yuhao Zhou, Jessica Hwang +2
Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems…
Double Control Variates for Gradient Estimation in Discrete Latent Variable Models
Michalis K. Titsias, Jiaxin Shi
Stochastic gradient-based optimisation for discrete latent variable models is challenging due to the high variance of gradients. We introduce a variance reduction technique for sco…
Gradient-based Adaptive Markov Chain Monte Carlo
Michalis K. Titsias, Petros Dellaportas
We introduce a gradient-based learning method to automatically adapt Markov chain Monte Carlo (MCMC) proposal distributions to intractable targets. We define a maximum entropy regu…