WorksMathematics
Classification of Forbidden 0-1 Patterns by Their Extremal Function
Abstract
This paper concerns the maximum weight of 0-1 matrices that avoid some pattern , denoted . Furedi and Hajnal initiated a research program of classifying all patterns according to their extremal function, but to date, only the weight-4 patterns are completely understood. In this paper we make progress on several fronts of the classification problem. A pattern is light if its columns have weight 1 and linear if . We characterize the set of weight-5 linear light patterns, and the set of weight-5 linear patterns more generally. Along the way we identify several new infinite classes of linear patterns, which support the Pettie-Tardos conjecture on characterizing all linear light patterns. It was known that there exist infinitely many minimally nonlinear patterns. We identify a specific infinite set of minimally nonlinear patterns. We also prove that there are weight- minimally nonlinear patterns, and that every minimally nonlinear pattern has extremal function , with the exception of the 4-cycle. We classify many of the outstanding weight-5 patterns according to their extremal function, leaving only a small set remaining. The newly classified weight-5 patterns have extremal function or . We also exhibit a large number of weight-6 patterns with extremal function , which is notable in that this function had not been encountered before for any single pattern , though it was known to be the correct extremal function for a pair of forbidden patterns.