Michal Moshkovitz

A General Memory-Bounded Learning Algorithm

2017 · arXiv (Cornell University)

Designing bounded-memory algorithms is becoming increasingly important nowadays. Previous works studying bounded-memory algorithms focused on proving impossibility results, while the design of bounded-memory algorithms was left relatively unexplored. To remedy this situation, in this work …

Towards a combinatorial characterization of bounded memory learning

2020 · arXiv (Cornell University)

Combinatorial dimensions play an important role in the theory of machine learning. For example, VC dimension characterizes PAC learning, SQ dimension characterizes weak learning with statistical queries, and Littlestone dimension characterizes online learning. In this …