Hacker News with Generative AI: Differentiation

An illustrated guide to automatic sparse differentiation (iclr-blogposts.github.io)
In numerous applications of machine learning, Hessians and Jacobians exhibit sparsity, a property that can be leveraged to vastly accelerate their computation.
Learning Category Trees for ID-Based Recommendation: Differentiable VQ (arxiv.org)
Category information plays a crucial role in enhancing the quality and personalization of recommender systems. Nevertheless, the availability of item category information is not consistently present, particularly in the context of ID-based recommendations.
Quaternion Differentiation (2012) (wordpress.com)