138 citations · 397 across the 26 of their papers we have counts for
4 papers · 1 filter
Thoughts on Massively Scalable Gaussian Processes
Andrew Gordon Wilson, Christoph Dann, Hannes Nickisch
We introduce a framework and early results for massively scalable Gaussian processes (MSGP), significantly extending the KISS-GP approach of Wilson and Nickisch (2015). The MSGP fr…
Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning
Christoph Dann, Emma Brunskill
Recently, there has been significant progress in understanding reinforcement learning in discounted infinite-horizon Markov decision processes (MDPs) by deriving tight sample compl…
The Human Kernel
Andrew Gordon Wilson, Christoph Dann, Christopher G. Lucas +1
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and a…
Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo
Amit Adam, Christoph Dann, Omer Yair +2
We propose a computational model for shape, illumination and albedo inference in a pulsed time-of-flight (TOF) camera. In contrast to TOF cameras based on phase modulation, our cam…