A Scalable Neural Network for DSIC Affine Maximizer Auction Design
This work addresses automated auction design for multi-item settings, offering a scalable solution that improves revenue performance, though it is incremental by enhancing existing affine maximizer approaches.
The paper tackled the scalability issue in designing dominant strategy incentive compatible (DSIC) affine maximizer auctions for multi-item scenarios, proposing AMenuNet, a neural network that ensures DSIC and individually rational properties while outperforming baselines in revenue and scaling to larger auctions.
Automated auction design aims to find empirically high-revenue mechanisms through machine learning. Existing works on multi item auction scenarios can be roughly divided into RegretNet-like and affine maximizer auctions (AMAs) approaches. However, the former cannot strictly ensure dominant strategy incentive compatibility (DSIC), while the latter faces scalability issue due to the large number of allocation candidates. To address these limitations, we propose AMenuNet, a scalable neural network that constructs the AMA parameters (even including the allocation menu) from bidder and item representations. AMenuNet is always DSIC and individually rational (IR) due to the properties of AMAs, and it enhances scalability by generating candidate allocations through a neural network. Additionally, AMenuNet is permutation equivariant, and its number of parameters is independent of auction scale. We conduct extensive experiments to demonstrate that AMenuNet outperforms strong baselines in both contextual and non-contextual multi-item auctions, scales well to larger auctions, generalizes well to different settings, and identifies useful deterministic allocations. Overall, our proposed approach offers an effective solution to automated DSIC auction design, with improved scalability and strong revenue performance in various settings.