Episode 28 | Karen Ullrich

A Coding Perspective on Deep Latent Variable Models

Papers and Links:

• Karen's Homepage
• Google Scholar
• Thesis
• David MacKay: Information Theory, Inference, and Learning Algorithms
• Cover & Thomas: Elements of Information Theory
• Keeping Neural Networks Simple by Minimizing the Description Length of the Weights
• Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
• Schmidhuber: Driven by Compression Progress

Listen: