Derives near-optimal regret bounds of O~(log N) for piecewise-linear and O~(N^{1/3}) for smooth primitives for a confidence-bound algorithm that learns the optimal dynamic bidding policy without explicit randomization.
A pragmatic policy learning approach to account for users’ fatigue in repeated auctions.arXiv preprint arXiv:2407.10504, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to Bid in Repeated Second-Price Auctions with Dynamic Values and Aggregated Feedback
Derives near-optimal regret bounds of O~(log N) for piecewise-linear and O~(N^{1/3}) for smooth primitives for a confidence-bound algorithm that learns the optimal dynamic bidding policy without explicit randomization.