Learning Optimal Auctions with Correlated Valuations from Samples

Authors: Chunxue Yang, Xiaohui Bei

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we investigate the robustness of the optimal auction with correlated valuations via sample complexity analysis. We prove upper and lower bounds on the number of samples from the unknown prior required to learn a (1 ϵ)-approximately optimal auction. Our results reinforce the common belief that optimal correlated auctions are sensitive to the distribution parameters and hard to learn unless the prior distribution is well-behaved. The paper focuses on theoretical proofs, lemmas, algorithm design (without empirical evaluation), and mathematical analysis of sample complexity bounds.
Researcher Affiliation Academia 1School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore. Correspondence to: Chunxue Yang <chunxue001@e.ntu.edu.sg>, Xiaohui Bei <xhbei@ntu.edu.sg>.
Pseudocode Yes Algorithm 1 Learning the bidder s payment in an empirical Cr emer-Mc Lean auction; Algorithm 2 Empirical Cr emer-Mc Lean Auction; Algorithm 3 Multi-Bidder Empirical Cr emer-Mc Lean Auction
Open Source Code No The paper does not provide any links to open-source code for the described methodology, nor does it explicitly state that code is available in supplementary materials or upon request.
Open Datasets No This paper is theoretical and does not use or reference any specific public datasets for training, validation, or testing.
Dataset Splits No This paper is theoretical and does not conduct experiments involving dataset splits. Thus, no training/validation/test splits are mentioned.
Hardware Specification No The paper is theoretical and focuses on mathematical proofs and algorithms. It does not describe any experimental setup or hardware used.
Software Dependencies No The paper is theoretical and presents algorithms and proofs. It does not describe any specific software dependencies or versions used for implementation or experimentation.
Experiment Setup No The paper is theoretical and does not describe any empirical experiments or their setup, including hyperparameters or training configurations.