# Trading Vector Data in Vector Databases

arXiv: https://arxiv.org/abs/2511.07139 · HTML: https://mlsanity.com/paper/2511.07139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 85 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Finite-Time Analysis of Kernelised Contextual Bandits](https://mlsanity.com/paper/1309.6869/) (2013)
- [Decentralized Federated Learning through Proxy Model Sharing](https://mlsanity.com/paper/2111.11343/) (2021)
- [A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge](https://mlsanity.com/paper/2310.11703/) (2023)
- [Causal Inference in Recommender Systems: A Survey and Future Directions](https://mlsanity.com/paper/2208.12397/) (2022)
- [Survey of Vector Database Management Systems](https://mlsanity.com/paper/2310.14021/) (2023)
- [Cost-Effective Online Multi-LLM Selection with Versatile Reward Models](https://mlsanity.com/paper/2405.16587/) (2024)
- [High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations](https://mlsanity.com/paper/2303.09855/) (2023)
- [ParlayANN: Scalable and Deterministic Parallel Graph-Based Approximate Nearest Neighbor Search Algorithms](https://mlsanity.com/paper/2305.04359/) (2023)
- [Data Pricing in Machine Learning Pipelines](https://mlsanity.com/paper/2108.07915/) (2021)
- [Variance reduced Shapley value estimation for trustworthy data valuation](https://mlsanity.com/paper/2210.16835/) (2022)
- [Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates](https://mlsanity.com/paper/1803.08586/) (2018)
- [Hierarchical Conversational Preference Elicitation with Bandit Feedback](https://mlsanity.com/paper/2209.06129/) (2022)
- [Meta-Learning Adversarial Bandit Algorithms](https://mlsanity.com/paper/2307.02295/) (2023)
- [A Survey of Data Pricing for Data Marketplaces](https://mlsanity.com/paper/2303.04810/) (2023)
- [FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients](https://mlsanity.com/paper/2405.02881/) (2024)
- [Second Order Methods for Bandit Optimization and Control](https://mlsanity.com/paper/2402.08929/) (2024)
- [FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2206.11408/) (2022)
- [AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics](https://mlsanity.com/paper/2407.20124/) (2024)
- [Continuous-in-time Limit for Bayesian Bandits](https://mlsanity.com/paper/2210.07513/) (2022)

## Abstract (arXiv)

Vector data trading is essential for cross-domain learning with vector databases, yet it remains largely unexplored. We study this problem under online learning, where sellers face uncertain retrieval costs and buyers provide stochastic feedback to posted prices. Three main challenges arise: (1) heterogeneous and partial feedback in configuration learning, (2) variable and complex feedback in pricing learning, and (3) inherent coupling between configuration and pricing decisions. We propose a hierarchical bandit framework that jointly optimizes retrieval configurations and pricing. Stage I employs contextual clustering with confidence-based exploration to learn effective configurations with logarithmic regret. Stage II adopts interval-based price selection with local Taylor approximation to estimate buyer responses and achieve sublinear regret. We establish theoretical guarantees with polynomial time complexity and validate the framework on four real-world datasets, demonstrating consistent improvements in cumulative reward and regret reduction compared with existing methods.