Sample completion, structured correlation, and Netflix problems
Leonardo N. Coregliano, Maryanthe Malliaris
Published: 2025/9/23
Abstract
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 characterize learnability in this model in terms of VCN${}_{k,k}$-dimension (essentially $k$-dependence from Shelah's classification theory). This model suggests a theoretical explanation for the success of certain algorithms in the 2006~Netflix Prize competition.