Probabilistic Models

This thesis explores the intersection of deep learning and probabilistic machine learning to enhance the capabilities of artificial intelligence. It addresses the limitations of Gaussian processes (GPs) in practical applications, particularly in comparison to neural networks (NNs), and proposes advancements such as improved approximations and a novel formulation of Bayesian optimization (BO) that seamlessly integrates deep learning methods. The contributions aim to enrich the interplay between deep learning and probabilistic ML, advancing the foundations of AI and fostering the development of more capable and reliable automated decision-making systems.

Despite their many desirable properties, Gaussian processes (GPs) are often compared unfavorably to deep neural networks (NNs) for …

We propose a framework that lifts the capabilities of graph convolutional networks (GCNs) to scenarios where no input graph is given …

We reformulate the computation of the acquisition function in Bayesian optimization (BO) as a probabilistic classification problem, providing advantages in scalability, flexibility, and representational capacity, while casting aside the limitations of tractability constraints on the model.

One weird trick to make exact inference in Bayesian logistic regression tractable.

Our proposed framework uses a joint probabilistic model and stochastic variational inference to improve the performance and robustness of graph convolutional networks (GCNs) in scenarios without input graph data, outperforming state-of-the-art algorithms on semi-supervised classification tasks.

A summary of notation, identities and derivations for the sparse variational Gaussian process (SVGP) framework.

We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent …

An in-depth practical guide to variational encoders from a probabilistic perspective.