# Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration

arXiv: https://arxiv.org/abs/2507.20268 · HTML: https://mlsanity.com/paper/2507.20268/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [Distribution-Free, Risk-Controlling Prediction Sets](https://mlsanity.com/paper/2101.02703/) (2021)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Estimating means of bounded random variables by betting](https://mlsanity.com/paper/2010.09686/) (2020)
- [Theoretical Foundations of Conformal Prediction](https://mlsanity.com/paper/2411.11824/) (2024)
- [Cross-Prediction-Powered Inference](https://mlsanity.com/paper/2309.16598/) (2023)
- [Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Prediction](https://mlsanity.com/paper/2210.03067/) (2022)
- [Semi-Supervised Risk Control via Prediction-Powered Inference](https://mlsanity.com/paper/2412.11174/) (2024)
- [Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systems](https://mlsanity.com/paper/2405.15415/) (2024)
- [CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network](https://mlsanity.com/paper/2205.05775/) (2022)
- [Localization as a key enabler of 6G wireless systems: A comprehensive survey and an outlook](https://mlsanity.com/paper/2302.02107/) (2023)
- [Federated Learning-Based Localization with Heterogeneous Fingerprint Database](https://mlsanity.com/paper/2203.15388/) (2022)
- [Calibrating Wireless AI via Meta-Learned Context-Dependent Conformal Prediction](https://mlsanity.com/paper/2501.14566/) (2025)
- [Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning](https://mlsanity.com/paper/2406.15819/) (2024)

## Built on by (most cited first, 1 of 1)

- [Reliable Inference in Edge-Cloud Model Cascades via Conformal Alignment](https://mlsanity.com/paper/2510.17543/) (2025)

## Abstract (arXiv)

Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable position estimates. One remedy is to employ synthetic labels produced by a (generally different) predictive model. But fine-tuning an additional predictor, as well as estimating residual bias of the synthetic labels, demands additional data, aggravating calibration data scarcity in wireless environments. This letter proposes an approach that efficiently uses limited calibration data to simultaneously fine-tune a predictor and estimate the bias of synthetic labels, yielding prediction sets with rigorous coverage guarantees. Experiments on a fingerprinting dataset validate the effectiveness of the proposed method.