Agnostic Online Learning and Excellent Sets

We use algorithmic methods from online learning to revisit a key idea from the interaction of model theory and combinatorics, the existence of large "indivisible" sets, called "$\epsilon$-excellent," in $k$-edge stable graphs (equivalently, Littlestone classes). These sets arise in the Stable Regularity Lemma, a theorem characterizing the appearance of irregular pairs in Szemer\'edi's celebrated Regularity Lemma. Translating to the language of probability, we find a quite different existence proof for $\epsilon$-excellent sets in Littlestone classes, using regret bounds in online learning. This proof applies to any $\epsilon < {1}/{2}$, compared to $< {1}/{2^{2k}}$ or so in the original proof. We include a second proof using closure properties and the VC theorem, with other advantages but weaker bounds. As a simple corollary, the Littlestone dimension remains finite under some natural modifications to the definition. A theme in these proofs is the interaction of two abstract notions of majority, arising from measure, and from rank or dimension; we prove that these densely often coincide and that this is characteristic of Littlestone (stable) classes. The last section lists several open problems.