572 citations
- University of CambridgeGB8 papers
- University of TorontoCA8 papers
- Cornell UniversityUS6 papers
- University of Central FloridaUS6 papers
- University of WyomingUS6 papers
- Meta (Israel)IL4 papers
- OpenAI (United States)US4 papers
- Carnegie Mellon UniversityUS3 papers
- Georgia Institute of TechnologyUS3 papers
- Google (United States)US3 papers
- Linköping UniversitySE3 papers
- Stanford UniversityUS3 papers
5 papers · 2 filters
Metropolis-Hastings Generative Adversarial Networks
Ryan Turner, Jane Hung, Eric Frank +2
We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distrib…
Probabilistic Meta-Representations Of Neural Networks
Theofanis Karaletsos, Peter Dayan, Zoubin Ghahramani
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn indep…
Antithetic and Monte Carlo kernel estimators for partial rankings
Maria Lomeli, Mark Rowland, Arthur Gretton +1
In the modern age, rankings data is ubiquitous and it is useful for a variety of applications such as recommender systems, multi-object tracking and preference learning. However, m…
Pathwise Derivatives for Multivariate Distributions
Martin Jankowiak, Theofanis Karaletsos
We exploit the link between the transport equation and derivatives of expectations to construct efficient pathwise gradient estimators for multivariate distributions. We focus on t…
Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit
Yang Cao, Zheng Wen, Branislav Kveton +1
Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with…