Optimizing with constraints: reparametrization and geometry.

Optimizing with constraints: reparametrization and geometry.

When training machine learning models, and deep networks in particular, we typically use gradient...概要を表示 When training machine learning models, and deep networks in particular, we typically use gradient-based methods. But if we require the weights to satisfy some constraints, things quickly get more complicated. Some of the most popular strategies for handling constraints, while seemingly very different at first sight, are deeply connected. In this post, we will explore these connections and demonstr

• PyTorch
• math
• 機械学習