156 citations · 440 across the 15 of their papers we have counts for
16 papers
Role of Human-AI Interaction in Selective Prediction
Elizabeth Bondi, Raphael Koster, Hannah Sheahan +5
Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable, particularly to improv…
Acquisition of Chess Knowledge in AlphaZero
Thomas McGrath, Andrei Kapishnikov, Nenad Tomašev +5
What is learned by sophisticated neural network agents such as AlphaZero? This question is of both scientific and practical interest. If the representations of strong neural networ…
Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess
Nenad Tomašev, Ulrich Paquet, Demis Hassabis +1
It is non-trivial to design engaging and balanced sets of game rules. Modern chess has evolved over centuries, but without a similar recourse to history, the consequences of rule c…
Unsupervised Separation of Dynamics from Pixels
Silvia Chiappa, Ulrich Paquet
We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way. We introduce a probabilistic model that first generate noisy positions…
A Factorial Mixture Prior for Compositional Deep Generative Models
Ulrich Paquet, Sumedh K. Ghaisas, Olivier Tieleman
We assume that a high-dimensional datum, like an image, is a compositional expression of a set of properties, with a complicated non-linear relationship between the datum and its p…
An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models
Ulrich Paquet, Marco Fraccaro
This technical report presents pseudo-code for a Riemannian manifold Hamiltonian Monte Carlo (RMHMC) method to efficiently simulate samples from -dimensional posterior distribut…
Recurrent Relational Networks
Rasmus Berg Palm, Ulrich Paquet, Ole Winther
This paper is concerned with learning to solve tasks that require a chain of interdependent steps of relational inference, like answering complex questions about the relationships…
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
Marco Fraccaro, Simon Kamronn, Ulrich Paquet +1
This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non…
The Bayesian Low-Rank Determinantal Point Process Mixture Model
Mike Gartrell, Ulrich Paquet, Noam Koenigstein
Determinantal point processes (DPPs) are an elegant model for encoding probabilities over subsets, such as shopping baskets, of a ground set, such as an item catalog. They are usef…
Sequential Neural Models with Stochastic Layers
Marco Fraccaro, Søren Kaae Sønderby, Ulrich Paquet +1
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue…
An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants
Marco Fraccaro, Ulrich Paquet, Ole Winther
The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and have the advantage of…
Low-Rank Factorization of Determinantal Point Processes for Recommendation
Mike Gartrell, Ulrich Paquet, Noam Koenigstein
Determinantal point processes (DPPs) have garnered attention as an elegant probabilistic model of set diversity. They are useful for a number of subset selection tasks, including p…
On the Convergence of Stochastic Variational Inference in Bayesian Networks
Ulrich Paquet
We highlight a pitfall when applying stochastic variational inference to general Bayesian networks. For global random variables approximated by an exponential family distribution,…
Scalable Bayesian Modelling of Paired Symbols
Ulrich Paquet, Noam Koenigstein, Ole Winther
We present a novel, scalable and Bayesian approach to modelling the occurrence of pairs of symbols (i,j) drawn from a large vocabulary. Observed pairs are assumed to be generated b…
One-class Collaborative Filtering with Random Graphs: Annotated Version
Ulrich Paquet, Noam Koenigstein
The bane of one-class collaborative filtering is interpreting and modelling the latent signal from the missing class. In this paper we present a novel Bayesian generative model for…
Perturbative Corrections for Approximate Inference in Gaussian Latent Variable Models
Manfred Opper, Ulrich Paquet, Ole Winther
Expectation Propagation (EP) provides a framework for approximate inference. When the model under consideration is over a latent Gaussian field, with the approximation being Gaussi…