Mode Connectivity in Auction Design

References

• [1] Allen-Zhu Z, Li Y, Song Z (2019) A convergence theory for deep learning via over-parameterization. Proc. 36th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 97 (PMLR, New York), 242–252.Google Scholar
• [2] Arora S, Ge R, Neyshabur B, Zhang Y (2018) Stronger generalization bounds for deep nets via a compression approach. Proc. 35th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 80 (PMLR, New York), 254–263.Google Scholar
• [3] Babaioff M, Gonczarowski YA, Nisan N (2022) The menu-size complexity of revenue approximation. Games Econom. Behav. 134(C):281–307.Crossref, Google Scholar
• [4] Bhalgat A, Gollapudi S, Munagala K (2013) Optimal auctions via the multiplicative weight method. Proc. 14th ACM Conf. Electronic Commerce (Association for Computing Machinery, New York), 73–90.Google Scholar
• [5] Cai Y, Daskalakis C, Weinberg SM (2012) An algorithmic characterization of multi-dimensional mechanisms. Proc. 44th Annual ACM Sympos. Theory Comput. (Association for Computing Machinery, New York), 459–478.Google Scholar
• [6] Cai Y, Daskalakis C, Weinberg SM (2012) Optimal multi-dimensional mechanism design: Reducing revenue to welfare maximization. 2012 IEEE 53rd Annual Sympos. Foundations Comput. Sci. (IEEE, New York), 130–139.Google Scholar
• [7] Cai Y, Daskalakis C, Weinberg SM (2013) Understanding incentives: Mechanism design becomes algorithm design. 2013 IEEE 54th Annual Sympos. Foundations Comput. Sci. (IEEE, New York), 618–627.Google Scholar
• [8] Clarke EH (1971) Multipart pricing of public goods. Public Choice 11:17–33.Crossref, Google Scholar
• [9] Conitzer V, Sandholm T (2002) Complexity of mechanism design. Darwiche A, Friedman N, eds. Proc. 18th Conf. Uncertainty Artificial Intelligence (Morgan Kaufmann Publishers Inc., San Francisco), 103–110.Google Scholar
• [10] Conitzer V, Sandholm T (2004) Self-interested automated mechanism design and implications for optimal combinatorial auctions. Proc. 5th ACM Conf. Electronic Commerce (Association for Computing Machinery, New York), 132–141.Google Scholar
• [11] Curry M, Sandholm T, Dickerson J (2022) Differentiable economics for randomized affine maximizer auctions. Preprint, submitted February 6, https://arxiv.org/abs/2202.02872.Google Scholar
• [12] Curry MJ, Lyi U, Goldstein T, Dickerson JP (2022) Learning revenue-maximizing auctions with differentiable matching. Proc. 25th Internat. Conf. Artificial Intelligence Statist., Proceedings of Machine Learning Research, vol. 151 (PMLR, New York), 6062–6073.Google Scholar
• [13] Daskalakis C (2015) Multi-item auctions defying intuition? ACM SIGecom Exchanges 14(1):41–75.Crossref, Google Scholar
• [14] Daskalakis C, Deckelbaum A, Tzamos C (2013) Mechanism design via optimal transport. Proc. 14th ACM Conf. Electronic Commerce (Association for Computing Machinery, New York), 269–286.Google Scholar
• [15] Daskalakis C, Deckelbaum A, Tzamos C (2014) The complexity of optimal mechanism design. Chekuri C, ed. Proc. 2014 Annual ACM-SIAM Sympos. Discrete Algorithms (SIAM, Philadelphia), 1302–1318.Google Scholar
• [16] Daskalakis C, Deckelbaum A, Tzamos C (2015) Strong duality for a multiple-good monopolist. Proc. 16th ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 449–450.Google Scholar
• [17] Draxler F, Veschgini K, Salmhofer M, Hamprecht F (2018) Essentially no barriers in neural network energy landscape. Proc. 35th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 80 (PMLR, New York), 1309–1318.Google Scholar
• [18] Du S, Lee J, Li H, Wang L, Zhai X (2019) Gradient descent finds global minima of deep neural networks. Proc. 36th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 97 (PMLR, New York), 1675–1685.Google Scholar
• [19] Duan Z, Tang J, Yin Y, Feng Z, Yan X, Zaheer M, Deng X (2022) A context-integrated transformer-based neural network for auction design. Proc. 39th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 162 (PMLR, New York), 5609–5626.Google Scholar
• [20] Dughmi S, Han L, Nisan N (2014) Sampling and representation complexity of revenue maximization. Liu TY, Qi Q, Ye Y, eds. Web Internet Econom. WINE 2014 (Springer, Cham, Switzerland), 277–291.Google Scholar
• [21] Dütting P, Feng Z, Narasimhan H, Parkes D, Ravindranath SS (2019) Optimal auctions through deep learning. Proc. 36th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 97 (PMLR, New York), 1706–1715.Google Scholar
• [22] Feng Z, Narasimhan H, Parkes DC (2018) Deep learning for revenue-optimal auctions with budgets. Proc. 17th Internat. Conf. Autonomous Agents Multiagent Systems (International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC), 354–362.Google Scholar
• [23] Garipov T, Izmailov P, Podoprikhin D, Vetrov DP, Wilson AG (2018) Loss surfaces, mode connectivity, and fast ensembling of DNNs. Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R, eds. Advances in Neural Information Processing Systems, vol. 31 (Curran Associates, Red Hook, NY).Google Scholar
• [24] Giannakopoulos Y, Koutsoupias E (2014) Duality and optimality of auctions for uniform distributions. Proc. 15th ACM Conf. Econom. Comput. (Association for Computing Machinery, New York), 259–276.Google Scholar
• [25] Giannakopoulos Y, Koutsoupias E (2018) Duality and optimality of auctions for uniform distributions. SIAM J. Comput. 47(1):121–165.Crossref, Google Scholar
• [26] Golowich N, Narasimhan H, Parkes DC (2018) Deep learning for multi-facility location mechanism design. Lang J, ed. Proc. 27th Internat. Joint Conf. Artificial Intelligence (International Joint Conferences on Artificial Intelligence), 261–267.Google Scholar
• [27] Groves T (1973) Incentives in teams. Econometrica 41(4):617–631.Crossref, Google Scholar
• [28] Hertrich C, Tao Y, Végh LA (2023) Mode connectivity in auction design. Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S, eds. Advances in Neural Information Processing Systems, vol. 36 (Curran Associates, Red Hook, NY), 52957–52968.Google Scholar
• [29] Kuditipudi R, Wang X, Lee H, Zhang Y, Li Z, Hu W, Ge R, Arora S (2019) Explaining landscape connectivity of low-cost solutions for multilayer nets. Wallach H, Larochelle H, Beygelzimer A, d’Alché-Buc F, Fox E, Garnett R, eds. Advances in Neural Information Processing Systems, vol. 32 (Curran Associates, Red Hook, NY).Google Scholar
• [30] Kuo K, Ostuni A, Horishny E, Curry MJ, Dooley S, Chiang P-Y, Goldstein T, Dickerson JP (2020) ProportionNet: Balancing fairness and revenue for auction design with deep learning. Preprint, submitted October 13, https://arxiv.org/abs/2010.06398.Google Scholar
• [31] Manelli AM, Vincent DR (2007) Multidimensional mechanism design: Revenue maximization and the multiple-good monopoly. J. Econom. Theory 137(1):153–185.Crossref, Google Scholar
• [32] Myerson RB (1981) Optimal auction design. Math. Oper. Res. 6(1):58–73.Link, Google Scholar
• [33] Nguyen Q (2019) On connected sublevel sets in deep learning. Proc. 36th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 97 (PMLR, New York), 4790–4799.Google Scholar
• [34] Rochet J-C (1987) A necessary and sufficient condition for rationalizability in a quasi-linear context. J. Math. Econom. 16(2):191–200.Crossref, Google Scholar
• [35] Rochet J-C, Stole LA (2003) The economics of multidimensional screening. Econometric Soc. Monographs 35:150–197.Google Scholar
• [36] Sandholm T, Likhodedov A (2015) Automated design of revenue-maximizing combinatorial auctions. Oper. Res. 63(5):1000–1025.Link, Google Scholar
• [37] Shen W, Tang P, Zuo S (2019) Automated mechanism design via neural networks. Proc. 18th Internat. Conf. Autonomous Agents Multiagent Systems (International Foundation for Autonomous Agents Multiagent Systems, Richland, SC), 215–223.Google Scholar
• [38] Shevchenko A, Mondelli M (2020) Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks. Daumé H, Singh A, eds. Proc. 37th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research (PMLR, New York), 8773–8784.Google Scholar
• [39] Vickrey W (1961) Counterspeculation, auctions, and competitive sealed tenders. J. Finance 16(1):8–37.Crossref, Google Scholar
• [40] Wang T, Jiang Y, Parkes DC (2024) GemNet: Menu-based, strategy-proof multi-bidder auctions through deep learning. Proc. 25th ACM Conf. Electronic Commerce (Association for Computing Machinery, New York), 1100.Google Scholar
• [41] Zheng S, Trott A, Srinivasa S, Parkes DC, Socher R (2022) The AI economist: Taxation policy design via two-level deep multiagent reinforcement learning. Sci. Adv. 8(18):1–17.Crossref, Google Scholar