8 citations · 20 across the 5 of their papers we have counts for
6 papers
VampPrior Unleashed
Andrew A. Stirn, Abhejit Rajagopal, David A. Knowles +1
Deep latent variable models (DLVMs) underpin many modern analysis pipelines, for example in single-cell genomics, yet their prior distributions have received markedly little attent…
The VampPrior Mixture Model
Andrew A. Stirn, David A. Knowles
Widely used deep latent variable models (DLVMs), in particular Variational Autoencoders (VAEs), employ overly simplistic priors on the latent space. To achieve strong clustering pe…
Faithful Heteroscedastic Regression with Neural Networks
Andrew Stirn, Hans-Hermann Wessels, Megan Schertzer +3
Heteroscedastic regression models a Gaussian variable's mean and variance as a function of covariates. Parametric methods that employ neural networks for these parameter maps can c…
Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
Andrew Stirn, David A. Knowles
Brittle optimization has been observed to adversely impact model likelihoods for regression and VAEs when simultaneously fitting neural network mappings from a (random) variable on…
A New Distribution on the Simplex with Auto-Encoding Applications
Andrew Stirn, Tony Jebara, David A Knowles
We construct a new distribution for the simplex using the Kumaraswamy distribution and an ordered stick-breaking process. We explore and develop the theoretical properties of this…
Thompson Sampling for Noncompliant Bandits
Andrew Stirn, Tony Jebara
Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many dom…