New Math Tool Could Make AI Recommendations Less Repetitive and More Surprising
This could mean better movie picks, news feeds, and shopping suggestions for you.
Determinantal point processes (DPPs) provide tractable distributions for nite random sets, but the usual symmetric-kernel specication imposes nonpositive pairwise dependence. Statistical research on nonsymmetric DPPs, which can accommodate positive dependence, remains limited. We study identication and estimation for this class.
First, we establish the equivalence of two sucient conditions for a nonsymmetric kernel to dene a valid DPP. Second, we develop the identication theory for nonsymmetric DPPs. Third, we develop cardinality-truncated maximum-likelihood estimation and estimation by averaged stochastic gradient descent.
Under suitable identication and regularity conditions, we establish consistency and asymptotic normality for both estimators. Simulations examine identication, the eects of truncation, and the nite-sample performance of the estimators. We illustrate the methods with two cyber applications at markedly dierent sampling frequencies: weekly sector-by-breach data and second-by-second enterprise authentication data with more than ve million set observations.
- A new mathematical method helps computers choose diverse sets of items, like movie recommendations that aren't all the same genre.
- It's called a nonsymmetric determinantal point process, and it's more flexible than older versions.
- This could lead to more varied and interesting suggestions in apps, but it's still early-stage research.
Why It Matters
Better AI recommendations could save you time and introduce you to new favorites.