Litcius/Paper detail

The Complexity of Gradient Descent: CLS = PPAD ∩ PLS

John Fearnley, Paul W. Goldberg, Alexandros Hollender, Rahul Savani

2022Journal of the ACM25 citationsDOI

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 ∩ 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 ∩ PLS and contains many interesting problems – is itself equal to PPAD ∩ PLS.

Topics & Concepts

CLs upper limitsGradient descentComputer scienceDescent (aeronautics)MathematicsArtificial intelligencePhysicsMedicineArtificial neural networkOptometryMeteorologyArtificial Intelligence in GamesGame Theory and ApplicationsAuction Theory and Applications