Search Results for author:
Found 5 papers, 0 papers with code
Improved Representation Learning Through Tensorized Autoencoders
The central question in representation learning is what constitutes a good or meaningful representation.
On the Influence of Enforcing Model Identifiability on Learning dynamics of Gaussian Mixture Models
A common way to learn and analyze statistical models is to consider operations in the model parameter space.
Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks
While VC Dimension does result in trivial generalisation error bounds in this setting as well, we show that transductive Rademacher complexity can explain the generalisation properties of graph convolutional networks for stochastic block models.
Towards Modeling and Resolving Singular Parameter Spaces using Stratifolds
We empirically show that using (natural) gradient descent on the smooth manifold approximation instead of the singular space allows us to avoid the attractor behavior and therefore improve the convergence speed in learning.
Near-Optimal Comparison Based Clustering
The goal of clustering is to group similar objects into meaningful partitions.
