Differentiable Economics for Randomized Affine Maximizer Auctions
This work addresses a gap in automated mechanism design for multi-bidder auctions, though it is incremental as it builds on existing differentiable economics approaches.
The paper tackles the problem of designing automated auctions that are perfectly strategyproof for multiple bidders, presenting a modified affine maximizer auction with lotteries that achieves competitive or superior revenue compared to prior methods.
A recent approach to automated mechanism design, differentiable economics, represents auctions by rich function approximators and optimizes their performance by gradient descent. The ideal auction architecture for differentiable economics would be perfectly strategyproof, support multiple bidders and items, and be rich enough to represent the optimal (i.e. revenue-maximizing) mechanism. So far, such an architecture does not exist. There are single-bidder approaches (MenuNet, RochetNet) which are always strategyproof and can represent optimal mechanisms. RegretNet is multi-bidder and can approximate any mechanism, but is only approximately strategyproof. We present an architecture that supports multiple bidders and is perfectly strategyproof, but cannot necessarily represent the optimal mechanism. This architecture is the classic affine maximizer auction (AMA), modified to offer lotteries. By using the gradient-based optimization tools of differentiable economics, we can now train lottery AMAs, competing with or outperforming prior approaches in revenue.