Multi-Item Mechanisms without Item-Independence: Learnability via Robustness
Multi-Item Mechanisms without Item-Independence: Learnability via Robustness
复制标题
没有项目独立性的多项目机制:通过鲁棒性实现可学习性
DOI:
10.1145/3391403.3399541
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Daskalakis, Constantinos
中科院分区:
文献类型:
--
作者:
Brustle, Johannes;Cai, Yang;Daskalakis, Constantinos
We study the sample complexity of learning revenue-optimal multi-item auctions. We obtain the first set of positive results that go beyond the standard but unrealistic setting of item-independence. In particular, we consider settings where bidders' valuations are drawn from correlated distributions that can be captured by Markov Random Fields or Bayesian Networks -- two of the most prominent graphical models. We establish parametrized sample complexity bounds for learning an up-to-ε optimal mechanism in both models, which scale polynomially in the size of the model, i.e. the number of items and bidders, and only exponential in the natural complexity measure of the model, namely either the largest in-degree (for Bayesian Networks) or the size of the largest hyper-edge (for Markov Random Fields).We obtain our learnability results through a novel and modular framework that involves first proving a robustness theorem. We show that, given only "approximate distributions" for bidder valuations, we can learn a mechanism whose revenue is nearly optimal simultaneously for all "true distributions" that are close to the ones we were given in Prokhorov distance. Thus, to learn a good mechanism, it suffices to learn approximate distributions. When item values are independent, learning in Prokhorov distance is immediate, hence our framework directly implies the main result of Gonczarowski and Weinberg[36]. When item values are sampled from more general graphical models, we combine our robustness theorem with novel sample complexity results for learning Markov Random Fields or Bayesian Networks in Prokhorov distance, which may be of independent interest. Finally, in the single-item case, our robustness result can be strengthened to hold under an even weaker distribution distance, the Levy distance.
登录
查看更多内容
DOI:
10.1137/1.9781611973075.49
发表时间:
2009
期刊:
ArXiv
影响因子:
--
作者:
Patrick Briest;Shuchi Chawla;Robert D. Kleinberg;S. Weinberg;A. P. Sloan;Foundation Fellowship
通讯作者:
Foundation Fellowship
DOI:
--
发表时间:
2011
期刊:
IEEE Annual Symposium on Foundations of Computer Science
影响因子:
--
作者:
Yang Cai;C. Daskalakis
通讯作者:
C. Daskalakis
DOI:
10.1145/3033274.3085120
发表时间:
2017
期刊:
Proceedings of the 2017 ACM Conference on Economics and Computation
影响因子:
--
作者:
A. Yao
通讯作者:
A. Yao
DOI:
10.1016/b978-0-12-386908-1.00037-9
发表时间:
2018-11
期刊:
Wiley Series in Probability and Statistics
影响因子:
--
作者:
Bruce E. Blaine
通讯作者:
Bruce E. Blaine
DOI:
10.1145/2764468.2764521
发表时间:
2015
期刊:
Proceedings of the Sixteenth ACM Conference on Economics and Computation
影响因子:
--
作者:
C. Daskalakis;Nikhil R. Devanur;S. M. Weinberg
通讯作者:
S. M. Weinberg