Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning
Vincent Abbott, Gioele Zardini
Despite deep learning models running well-defined mathematical functions, we lack a formal mathematical framework for describing model architectures. Ad-hoc notation, diagrams, and…
cs.LG2025
FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness
Vincent Abbott, Gioele Zardini
Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 perfor…