4 papers
Sample completion, structured correlation, and Netflix problems
Leonardo N. Coregliano, Maryanthe Malliaris
We develop a new high-dimensional statistical learning model which can take advantage of structured correlation in data even in the presence of randomness. We completely characteri…
A packing lemma for VCN-dimension and learning high-dimensional data
Leonardo N. Coregliano, Maryanthe Malliaris
Recently, the authors introduced the theory of high-arity PAC learning, which is well-suited for learning graphs, hypergraphs and relational structures. In the same initial work, t…
On the equivalence of quasirandomness and exchangeable representations independent from lower-order variables
Leonardo N. Coregliano, Henry P. Towsner
It is often convenient to represent a process for randomly generating a graph as a graphon. (More precisely, these give \emph{vertex exchangeable} processes -- those processes in w…
On the Density of Transitive Tournaments
Leonardo Nagami Coregliano, Alexander A. Razborov
We prove that for every fixed , the number of occurrences of the transitive tournament of order in a tournament on vertices is asymptotically minimized when…