Revenue maximization learning curves converge arbitrarily slowly without restrictions, at rate roughly 1/sqrt(n) when optimal revenue uses a finite price, and almost exponentially for discrete valuation supports.
Alkis Kalavasis, Grigoris Velegkas, and Amin Karbasi
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A hypothesis class is learnable in this online precision-recall feedback model if and only if it has finite VC dimension, with algorithms achieving regret bounds in realizable and agnostic settings despite ERM failing.
citing papers explorer
-
On the Learning Curves of Revenue Maximization
Revenue maximization learning curves converge arbitrarily slowly without restrictions, at rate roughly 1/sqrt(n) when optimal revenue uses a finite price, and almost exponentially for discrete valuation supports.
-
Online Set Learning from Precision and Recall Feedback
A hypothesis class is learnable in this online precision-recall feedback model if and only if it has finite VC dimension, with algorithms achieving regret bounds in realizable and agnostic settings despite ERM failing.