no code implementations • 5 Dec 2022 • Alexander Razborov
We continue a long line of research aimed at proving convergence of depth 2 neural networks, trained via gradient descent, to a global minimum.
no code implementations • 17 Dec 2020 • Albert Atserias, Ilario Bonacina, Susanna F. de Rezende, Massimo Lauria, Jakob Nordström, Alexander Razborov
We prove that for $k \ll \sqrt[4]{n}$ regular resolution requires length $n^{\Omega(k)}$ to establish that an Erd\H{o}s-R\'enyi graph with appropriately chosen edge density does not contain a $k$-clique.
Computational Complexity
