# Generalized Gradient Descent is a Hypergraph Functor

arXiv: https://arxiv.org/abs/2403.19845 · HTML: https://mlsanity.com/paper/2403.19845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Categorical Foundations of Gradient-Based Learning](https://mlsanity.com/paper/2103.01931/) (2021)
- [Reverse derivative categories](https://mlsanity.com/paper/1910.07065/) (2019)
- [Hypergraph Categories](https://mlsanity.com/paper/1806.08304/) (2018)
- [Rethinking Hard-Parameter Sharing in Multi-Domain Learning](https://mlsanity.com/paper/2107.11359/) (2021)
- [A Compositional Framework for First-Order Optimization](https://mlsanity.com/paper/2403.05711/) (2024)
- [Generalized Optimization: A First Step Towards Category Theoretic Learning Theory](https://mlsanity.com/paper/2109.10262/) (2021)

## Abstract (arXiv)

Cartesian reverse derivative categories (CRDCs) provide an axiomatic generalization of the reverse derivative, which allows generalized analogues of classic optimization algorithms such as gradient descent to be applied to a broad class of problems. In this paper, we show that generalized gradient descent with respect to a given CRDC induces a hypergraph functor from a hypergraph category of optimization problems to a hypergraph category of dynamical systems. The domain of this functor consists of objective functions that are 1) general in the sense that they are defined with respect to an arbitrary CRDC, and 2) open in that they are decorated spans that can be composed with other such objective functions via variable sharing. The codomain is specified analogously as a category of general and open dynamical systems for the underlying CRDC. We describe how the hypergraph functor induces a distributed optimization algorithm for arbitrary composite problems specified in the domain. To illustrate the kinds of problems our framework can model, we show that parameter sharing models in multitask learning, a prevalent machine learning paradigm, yield a composite optimization problem for a given choice of CRDC. We then apply the gradient descent functor to this composite problem and describe the resulting distributed gradient descent algorithm for training parameter sharing models.