An online pricing-and-allocation algorithm with lower-confidence-bound agent selection achieves O~(sqrt(T) mn) regret, but the proof rests on a false convexity lemma.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Online Pricing and Allocation with Demand Learning and Fulfillment Cost
An online pricing-and-allocation algorithm with lower-confidence-bound agent selection achieves O~(sqrt(T) mn) regret, but the proof rests on a false convexity lemma.