The Price of Ignorance: Information-Free Quotation for Data Retention in Machine Unlearning

• URL: http://arxiv.org/abs/2604.11511v1
• Date: Mon, 13 Apr 2026 14:14:35 GMT
• Title: The Price of Ignorance: Information-Free Quotation for Data Retention in Machine Unlearning
• Abstract summary: We design an information-free ascending quotation mechanism where users self-select their data supply, requiring no knowledge of users' parameters.<n>We formalize the Price of Ignorance -- the welfare gap between optimal personalized pricing (which knows everything) and our information-free quotation (which knows nothing)
• Score: 9.926764766573056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When users exercise data deletion rights under the General Data Protection Regulation (GDPR) and similar regulations, mobile network operators face a tradeoff: excessive machine unlearning degrades model accuracy and incurs retraining costs, yet existing pricing mechanisms for data retention require the server to know every user's private privacy and accuracy preferences, which is infeasible under the very regulations that motivate unlearning. We ask: what is the welfare cost of operating without this private information? We design an information-free ascending quotation mechanism where the server broadcasts progressively higher prices and users self-select their data supply, requiring no knowledge of users' parameters. Under complete information, the protocol admits a unique subgame-perfect Nash equilibrium characterized by single-period selling. We formalize the Price of Ignorance -- the welfare gap between optimal personalized pricing (which knows everything) and our information-free quotation (which knows nothing) -- and prove a three-regime efficiency ordering. Numerical evaluation across seven mechanisms and 5000 Monte Carlo runs shows that this price is near zero: the information-free mechanism achieves >=99% of the welfare of its information-intensive benchmarks, while providing noise-robust guarantees and comparable fairness.

Related papers

• Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data [56.86147283213652]
  We present a customizable empirical auditing framework designed to detect and explain data disclosures.<n>Our framework introduces a mechanism to distinguish between "true disclosures"-where the system directly reproduces a user's information-and "phantom disclosures"-where the system incidentally generates a user's data.
  arXiv  Detail & Related papers  (2026-06-15T16:54:02Z)
• NH-CROP: Robust Pricing for Governed Language Data Assets under Cost Uncertainty [7.123785374544969]
  We study online pricing for governed language data assets under cost uncertainty.<n>We introduce textscNH-CROP, a clipped robust pricing framework with a no-harm information-acquisition gate.
  arXiv  Detail & Related papers  (2026-05-03T06:48:50Z)
• A Sustainable AI Economy Needs Data Deals That Work for Generators [56.949279542190084]
  We argue that the machine learning value chain is structurally unsustainable due to an economic data processing inequality.<n>We analyze 73 public data deals and show that the majority of value accrues to aggregators.<n>We propose an Equitable Data-Value Exchange Framework to enable a minimal market that benefits all participants.
  arXiv  Detail & Related papers  (2026-01-15T01:05:48Z)
• Designing DSIC Mechanisms for Data Sharing in the Era of Large Language Models [0.0]
  Training large language models (LLMs) requires vast amounts of high-quality data from institutions that face legal, privacy, and strategic constraints.<n>We introduce a mechanism-design framework for truthful, trust-minimized data sharing.<n>We formalize a model where providers privately know their data cost and quality, and value arises solely from the data's contribution to model performance.
  arXiv  Detail & Related papers  (2025-06-01T22:17:18Z)
• Buyer-Initiated Auction Mechanism for Data Redemption in Machine Unlearning [10.43572220941666]
  rapid growth of artificial intelligence (AI) has raised privacy concerns.<n>Leading regulations like California Consumer Privacy Act (CCPA)<n>We propose buyer-initiated auction mechanism for data redemption.
  arXiv  Detail & Related papers  (2025-03-29T07:44:34Z)
• Wasserstein Markets for Differentially-Private Data [1.4266656344673316]
  Data markets provide a means to enable wider access as well as determine the appropriate privacy-utility trade-off.<n>Existing data market frameworks either require a trusted third party to perform expensive valuations or are unable to capture the nature of data value.<n>This paper proposes a valuation mechanism based on the Wasserstein distance for differentially-private data, and corresponding procurement mechanisms.
  arXiv  Detail & Related papers  (2024-12-03T17:40:26Z)
• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy [51.11280118806893]
  We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. We study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP) More specifically, we advance the existing literature by deriving tight $f$-DP guarantees for a variety of discrete-valued mechanisms.
  arXiv  Detail & Related papers  (2023-02-19T16:58:53Z)
• Mechanisms that Incentivize Data Sharing in Federated Learning [90.74337749137432]
  We show how a naive scheme leads to catastrophic levels of free-riding where the benefits of data sharing are completely eroded. We then introduce accuracy shaping based mechanisms to maximize the amount of data generated by each agent.
  arXiv  Detail & Related papers  (2022-07-10T22:36:52Z)
• Data Sharing Markets [95.13209326119153]
  We study a setup where each agent can be both buyer and seller of data. We consider two cases: bilateral data exchange (trading data with data) and unilateral data exchange (trading data with money)
  arXiv  Detail & Related papers  (2021-07-19T06:00:34Z)
• Towards Probabilistic Verification of Machine Unlearning [30.892906429582904]
  We propose a formal framework to study the design of verification mechanisms for data deletion requests. We show that our approach has minimal effect on the machine learning service's accuracy but provides high confidence verification of unlearning.
  arXiv  Detail & Related papers  (2020-03-09T16:39:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.