arXiv:2011.01929cs.CC
The Complexity of Gradient Descent: CLS = PPAD $\cap$ PLS
Abstract
We study search problems that can be solved by performing Gradient Descent on a bounded convex polytopal domain and show that this class is equal to the intersection of two well-known classes: PPAD and PLS. As our main underlying technical contribution, we show that computing a Karush-Kuhn-Tucker (KKT) point of a continuously differentiable function over the domain $[0,1]^2$ is PPAD $\cap$ PLS-complete. This is the first non-artificial problem to be shown complete for this class. Our results also imply that the class CLS (Continuous Local Search) - which was defined by Daskalakis and Papadimitriou as a more "natural" counterpart to PPAD $\cap$ PLS and contains many interesting problems - is itself equal to PPAD $\cap$ PLS.
https://arxiv.org/abs/2011.01929 TFP
ShamelessCView on HNParent context
Here's the original paper: https://arxiv.org/abs/2011.01929 And here are the complexity classes that are mentioned in the abstract: https://complexityzoo.net/Complexity_Zoo:P#ppad and https://complexityzoo.net/Complexity_Zoo:P#pls.
eterevskyView on HNParent context