Search Results for author:
Found 5 papers, 4 papers with code
The VampPrior Mixture Model
Current clustering priors for deep latent variable models (DLVMs) require defining the number of clusters a-priori and are susceptible to poor initializations.
Ranked #2 on
Image Clustering
on Fashion-MNIST
Faithful Heteroscedastic Regression with Neural Networks
For a wide variety of network and task complexities, we find that mean estimates from existing heteroscedastic solutions can be significantly less accurate than those from an equivalently expressive mean-only model.
Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
Brittle optimization has been observed to adversely impact model likelihoods for regression and VAEs when simultaneously fitting neural network mappings from a (random) variable onto the mean and variance of a dependent Gaussian variable.
A New Distribution on the Simplex with Auto-Encoding Applications
We construct a new distribution for the simplex using the Kumaraswamy distribution and an ordered stick-breaking process.
Thompson Sampling for Noncompliant Bandits
Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many domains.
