Alexander Kozachinskiy

Alexander Kozachinskiy

Especialidad: Algorithms, information theory, algorithmic game theory, foundations of machine learning, complexity theory.
Alexander Kozachinskiy posee un PhD en Physics and Mathematics. Obtuvo este grado de la Lomonosov Moscow State University en 2019. Ha trabajado en el proyecto llamado "Expressive power of deep learning architectures", y es el investigador principal del Fondecyt iniciación N° 11250060.

PUBLICACIONES

Publisher:  LATIN 2024: Theoretical Informatics Link>

ABSTRACT

In this paper, we construct a winning condition W over a finite set of colors such that, first, every finite arena has a strategy with 2 states of general memory which is optimal w.r.t. W, and second, there exists no k such that every finite arena has a strategy with k states of chromatic memory which is optimal w.r.t. W.

agencia nacional de investigación y desarrollo
Edificio de Innovación UC, Piso 2
Vicuña Mackenna 4860
Macul, Chile