Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEquilibria in Auctions With Ad Types
98
0
0.0
(
0
)
Added by
Hadi Elzayn
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper studies equilibrium quality of semi-separable position auctions (known as the Ad Types setting) with greedy or optimal allocation combined with generalized second-price (GSP) or Vickrey-Clarke-Groves (VCG) pricing. We make three contributions: first, we give upper and lower bounds on the Price of Anarchy (PoA) for auctions which use greedy allocation with GSP pricing, greedy allocations with VCG pricing, and optimal allocation with GSP pricing. Second, we give Bayes-Nash equilibrium characterizations for two-player, two-slot instances (for all auction formats) and show that there exists both a revenue hierarchy and revenue equivalence across some formats. Finally, we use no-regret learning algorithms and bidding data from a large online advertising platform and no-regret learning algorithms to evaluate the performance of the mechanisms under semi-realistic conditions. For welfare, we find that the optimal-to-realized welfare ratio (an empirical PoA analogue) is broadly better than our upper bounds on PoA; For revenue, we find that the hierarchy in practice may sometimes agree with simple theory, but generally appears sensitive to the underlying distribution of bidder valuations.
rate research
Read More
Modern ad auctions allow advertisers to target more specific segments of the user population. Unfortunately, this is not always in the best interest of the ad platform. In this paper, we examine the following basic question in the context of second-price ad auctions: how should an ad platform optimally reveal information about the ad opportunity to the advertisers in order to maximize revenue? We consider a model in which bidders valuations depend on a random state of the ad opportunity. Different from previous work, we focus on a more practical, and challenging, situation where the space of possible realizations of ad opportunities is extremely large. We thus focus on developing algorithms whose running time is independent of the number of ad opportunity realizations. We examine the auctioneers algorithmic question of designing the optimal signaling scheme. When the auctioneer is restricted to send a public signal to all bidders, we focus on a well-motivated Bayesian valuation setting in which the auctioneer and bidders both have private information, and present two main results: 1. we exhibit a characterization result regarding approximately optimal schemes and prove that any constant-approximate public signaling scheme must use exponentially many signals; 2. we present a simple public signaling scheme that serves as a constant approximation under mild assumptions. We then initiate an exploration on the power of being able to send different signals privately to different bidders. Here we examine a basic setting where the auctioneer knows bidders valuations, and exhibit a polynomial-time private scheme that extracts almost full surplus even in the worst Bayes Nash equilibrium. This illustrates the surprising power of private signaling schemes in extracting revenue.
In this work we investigate the strategic learning implications of the deployment of sponsored search auction mechanisms that obey to fairness criteria. We introduce a new class of mechanisms composing a traditional Generalized Second Price auction (GSP) with different fair division schemes to achieve some desired level of fairness between two groups of Bayesian strategic advertisers. We propose two mechanisms, $beta$-Fair GSP and GSP-EFX, that compose GSP with, respectively, an envy-free up to one item (EF1), and an envy-free up to any item (EFX) fair division scheme. The payments of GSP are adjusted in order to compensate the advertisers that suffer a loss of efficiency due the fair division stage. We prove that, for both mechanisms, if bidders play so as to minimize their external regret they are guaranteed to reach an equilibrium with good social welfare. We also prove that the mechanisms are budget balanced, so that the payments charged by the traditional GSP mechanism are a good proxy of the total compensation offered to the advertisers. Finally, we evaluate the quality of the allocations of the two mechanisms through experiments on real-world data.
The Ad Types Problem (without gap rules) is a special case of the assignment problem in which there are $k$ types of nodes on one side (the ads), and an ordered set of nodes on the other side (the slots). The edge weight of an ad $i$ of type $theta$ to slot $j$ is $v_icdot alpha^{theta}_j$ where $v_i$ is an advertiser-specific value and each ad type $theta$ has a discount curve $alpha^{(theta)}_{1} ge alpha^{(theta)}_{2} ge ... ge 0$ over the slots that is common for ads of type $theta$. We present two contributions for this problem: 1) we give an algorithm that finds the maximum weight matching that runs in $O(n^2(k + log n))$ time for $n$ slots and $n$ ads of each type---cf. $O(kn^3)$ when using the Hungarian algorithm---, and 2) we show to do VCG pricing in asymptotically the same time, namely $O(n^2(k + log n))$, and apply reserve prices in $O(n^3(k + log n))$. The Ad Types Problem (with gap rules) includes a matrix $G$ such that after we show an ad of type $theta_i$, the next $G_{ij}$ slots cannot show an ad of type $theta_j$. We show that the problem is hard to approximate within $k^{1- epsilon}$ for any $epsilon > 0$ (even without discount curves) by reduction from Maximum Independent Set. On the positive side, we show a Dynamic Program formulation that solves the problem (including discount curves) optimally and runs in $O(kcdot n^{2k + 1})$ time.
In this paper we investigate the problem of measuring end-to-end Incentive Compatibility (IC) regret given black-box access to an auction mechanism. Our goal is to 1) compute an estimate for IC regret in an auction, 2) provide a measure of certainty around the estimate of IC regret, and 3) minimize the time it takes to arrive at an accurate estimate. We consider two main problems, with different informational assumptions: In the emph{advertiser problem} the goal is to measure IC regret for some known valuation $v$, while in the more general emph{demand-side platform (DSP) problem} we wish to determine the worst-case IC regret over all possible valuations. The problems are naturally phrased in an online learning model and we design $Regret-UCB$ algorithms for both problems. We give an online learning algorithm where for the advertiser problem the error of determining IC shrinks as $OBig(frac{|B|}{T}cdotBig(frac{ln T}{n} + sqrt{frac{ln T}{n}}Big)Big)$ (where $B$ is the finite set of bids, $T$ is the number of time steps, and $n$ is number of auctions per time step), and for the DSP problem it shrinks as $OBig(frac{|B|}{T}cdotBig( frac{|B|ln T}{n} + sqrt{frac{|B|ln T}{n}}Big)Big)$. For the DSP problem, we also consider stronger IC regret estimation and extend our $Regret-UCB$ algorithm to achieve better IC regret error. We validate the theoretical results using simulations with Generalized Second Price (GSP) auctions, which are known to not be incentive compatible and thus have strictly positive IC regret.
We study correlated equilibria and coarse equilibria of simple first-price single-item auctions in the simplest auction model of full information. Nash equilibria are known to always yield full efficiency and a revenue that is at least the second-highest value. We prove that the same is true for all correlated equilibria, even those in which agents overbid -- i.e., bid above their values. Coarse equilibria, in contrast, may yield lower efficiency and revenue. We show that the revenue can be as low as 26% of the second-highest value in a coarse equilibrium, even if agents are assumed not to overbid, and this is tight. We also show that when players do not overbid, the worst-case bound on social welfare at coarse equilibrium improves from 63% of the highest value to 81%, and this bound is tight as well.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
