The paper proposes two neural-network architectures for learning randomized combinatorial auction mechanisms and reports revenue gains over baselines, but the feasibility guarantee for the learned allocations is not proven.
The winner's curse, reserve prices, and endogenous entry: Empirical insights from ebay auctions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Advancing Differentiable Economics: A Neural Network Framework for Revenue-Maximizing Combinatorial Auction Mechanisms
The paper proposes two neural-network architectures for learning randomized combinatorial auction mechanisms and reports revenue gains over baselines, but the feasibility guarantee for the learned allocations is not proven.