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 $< {1}/{2^{2^k}}$ 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.
翻译:我们使用在线学习的算法方法,重新审视模型理论和组合法相互作用中的一个关键概念,即存在大型“不可变”的“不可变”组,称为“$\ epsilon$-excellent”,在$k$的前沿稳定图表中(相当于,Littlestone类),这些组是在Szemer\'edi所颂扬的规律 Lemma中非正常配对外表特征的一个理论性格。我们用概率语言转换,我们发现在Littolstone类中,使用网上学习的遗憾界限,存在一个非常不同的“不可变”组的存在证据。这个证据适用于任何$\ epslon < {1}/{{{2}}$,而原始证据中则是$ < {1}/ {{%2}/\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ 左右。我们用关闭属性属性的文字来作为第二个证据。作为一个简单的推论,我们从最深层的图层中可以证明,这些矩阵的特征的比。