English

Popularity Bias Alignment Estimates

Information Retrieval 2025-11-26 v1 Artificial Intelligence Machine Learning

Abstract

We are extending Popularity Bias Memorization theorem from arXiv:archive/2404.12008 in several directions. We extend it to arbitrary degree distributions and also prove both upper and lower estimates for the alignment with top-k singular hyperspace.

Cite

@article{arxiv.2511.19999,
  title  = {Popularity Bias Alignment Estimates},
  author = {Anton Lyubinin},
  journal= {arXiv preprint arXiv:2511.19999},
  year   = {2025}
}
R2 v1 2026-07-01T07:53:42.451Z