4.4k citations · 6.2k across the 79 of their papers we have counts for
10 papers · 1 filter
GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
Daniel Lengyel, Janith Petangoda, Isak Falk +5
We propose an efficient algorithm to visualise symmetries in neural networks. Typically, models are defined with respect to a parameter space, where non-equal parameters can produc…
Pathwise Conditioning of Gaussian Processes
James T. Wilson, Viacheslav Borovitskiy, Alexander Terenin +2
As Gaussian processes are used to answer increasingly complex questions, analytic solutions become scarcer and scarcer. Monte Carlo methods act as a convenient bridge for connectin…
Matérn Gaussian Processes on Graphs
Viacheslav Borovitskiy, Iskander Azangulov, Alexander Terenin +3
Gaussian processes are a versatile framework for learning unknown functions in a manner that permits one to utilize prior information about their properties. Although many differen…
A Foliated View of Transfer Learning
Janith Petangoda, Nick A. M. Monk, Marc Peter Deisenroth
Transfer learning considers a learning process where a new task is solved by transferring relevant knowledge from known solutions to related tasks. While this has been studied expe…
Probabilistic Active Meta-Learning
Jean Kaddour, Steindór Sæmundsson, Marc Peter Deisenroth
Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this prob…
Estimating Barycenters of Measures in High Dimensions
Samuel Cohen, Michael Arbel, Marc Peter Deisenroth
Barycentric averaging is a principled way of summarizing populations of measures. Existing algorithms for estimating barycenters typically parametrize them as weighted sums of Dira…
Stochastic Differential Equations with Variational Wishart Diffusions
Martin Jørgensen, Marc Peter Deisenroth, Hugh Salimbeni
We present a Bayesian non-parametric way of inferring stochastic differential equations for both regression tasks and continuous-time dynamical modelling. The work has high emphasi…
Aligning Time Series on Incomparable Spaces
Samuel Cohen, Giulia Luise, Alexander Terenin +2
Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in comparable spaces. In this work, we consider a sett…
Matérn Gaussian processes on Riemannian manifolds
Viacheslav Borovitskiy, Alexander Terenin, Peter Mostowsky +1
Gaussian processes are an effective model class for learning unknown functions, particularly in settings where accurately representing predictive uncertainty is of key importance.…
Efficiently Sampling Functions from Gaussian Process Posteriors
James T. Wilson, Viacheslav Borovitskiy, Alexander Terenin +2
Gaussian processes are the gold standard for many real-world modeling problems, especially in cases where a model's success hinges upon its ability to faithfully represent predicti…