Bidder Selection Problem in Position Auctions via Poisson Approximation

We consider Bidder Selection Problem (BSP) in position auctions motivated by practical concerns of online advertising platforms. In this problem, the platform sells ad slots via an auction to a large pool of $n$ potential buyers with independent values drawn from known prior distributions. The seller can only invite a fraction of $k<n$ advertisers to the auction due to communication and computation restrictions. She wishes to maximize either the social welfare or her revenue by selecting the set of invited bidders. We study BSP in a classic multi-winner model of position auctions for welfare and revenue objectives using the optimal (respectively, VCG mechanism, or Myerson's auction) format for the selected set of bidders. We propose a novel Poisson-Chernoff relaxation of the problem that immediately implies that 1) BSP is polynomial time solvable up to a vanishingly small error as the problem size $k$ grows; 2) PTAS for position auctions after combining our relaxation with the trivial brute force algorithm; the algorithm is in fact an Efficient PTAS (EPTAS) under a mild assumption $k\ge\log n$ with much better running time than previous PTASes for single-item auction. Our approach yields simple and practically relevant algorithms unlike all previous complex PTASes, which had at least doubly exponential dependency of their running time on $\varepsilon$. In contrast, our algorithms are even faster than popular algorithms such as greedy for submodular maximization. Furthermore, we did extensive numerical experiments, which demonstrate high efficiency and practical applicability of our solution. Our experiments corroborate the experimental findings of [Mehta, Nadav, Psomas, Rubinstein 2020] that many simple heuristics perform surprisingly well, which indicates importance of using small $\varepsilon$ for the BSP and practical irrelevance of all previous PTAS approaches.