Infinite-color randomly reinforced urns with dominant colors
Hristo Sariev, Sandra Fortini, Sonia Petrone

TL;DR
This paper studies a class of reinforced urn processes with dominant colors, proving almost sure convergence of distributions and exploring implications for Bayesian inference, clinical trials, and species sampling.
Contribution
It introduces and analyzes dominant Pólya sequences with unbounded colors, establishing convergence results and rates, and discusses potential applications.
Findings
Predictive and empirical distributions converge almost surely to a random measure.
Dominant colors with maximum expected reinforcement dominate the process.
Convergence rates are provided for the distributions.
Abstract
We define and prove limit results for a class of dominant P\'olya sequences, which are randomly reinforced urn processes with color-specific random weights and unbounded number of possible colors. Under fairly mild assumptions on the expected reinforcement, we show that the predictive and the empirical distributions converge almost surely (a.s.) in total variation to the same random probability measure ; moreover, a.s., where denotes the set of dominant colors for which the expected reinforcement is maximum. In the general case, the predictive probabilities and the empirical frequencies of any -neighborhood of converge a.s. to one. That is, although non-dominant colors continue to be regularly observed, their distance to converges in probability to zero. We refine the above results with rates of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputational Geometry and Mesh Generation
