Reproduce “Optimal Contextual Pricing in Non-Stationary Environments” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yiding Feng, Alireza Rezaeimoghadam
The authors present a deterministic multiscale pricing algorithm for contextual buyers whose values change under a known variation budget. It maintains pricing tolerances to handle stale purchase feedback, exploring when uncertainty is high and exploiting with the smallest viable set. Against an oracle pricing each buyer’s value, its regret is O((d² + d^(3/2)√(TV)) log² T), near-optimal up to logarithmic factors for fixed dimension, but dimension dependence is not claimed optimal.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.