A Market Framework for Eliciting Private Data
Authors: Bo Waggoner, Rafael Frongillo, Jacob D. Abernethy
NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We propose a mechanism for purchasing information from a sequence of participants. The mechanism, which draws on the principles of prediction markets, has a bounded budget and minimizes generalization error for Bregman divergence loss functions. We then show how to modify this mechanism to preserve the privacy of participants’ information: At any given time, the current prices and predictions of the mechanism reveal almost no information about any one participant, yet in total over all participants, information is accurately aggregated. (From Abstract) and The implication is that traders are incentivized to minimize a KL divergence between the market’s estimate of the distribution and the true underlying distribution. We refer to this property as incentive-compatibility because traders’ interests are aligned with the mechanism designer’s. This property indeed holds generally for Mechanism 1, where the KL divergence is replaced with a general Bregman divergence corresponding to the Fenchel conjugate of Cx( ); see Proposition 1 in the appendix for details. (From Section 2.2) and Theorem 2. Consider Mechanism 2, where is the maximimum trade size (Equation 3) and d = |Y|. Then Mechanism 2 is (ϵ, δ) differentially private and, with T traders and Q price queries, has the following accuracy guarantee: with probability 1 γ, for each query x the returned prices satisfy Cx( ˆf t) Cx(f t) α by setting γ ln 2 log T / (ϵ2δ log(T )3). (From Section 3.2). The paper designs and analyzes a theoretical framework. |
| Researcher Affiliation | Academia | Bo Waggoner Harvard SEAS bwaggoner@fas.harvard.edu Rafael Frongillo University of Colorado raf@colorado.edu Jacob Abernethy University of Michigan jabernet@umich.edu |
| Pseudocode | Yes | Mechanism 1: The Market Template" (Page 3) and "Mechanism 2: Privacy Protected Market" (Page 6) are presented as structured algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement or link indicating the availability of open-source code for the described methodology. |
| Open Datasets | No | The paper proposes a theoretical mechanism and does not conduct empirical experiments, therefore no dataset access information for training is provided. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments with dataset splits for validation. |
| Hardware Specification | No | The paper is theoretical and does not describe any empirical experiments, thus no hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical and does not describe any specific software implementations or list software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not report on empirical experiments, therefore no experimental setup details such as hyperparameter values are provided. |