# Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees

arXiv: https://arxiv.org/abs/2402.00899 · HTML: https://mlsanity.com/paper/2402.00899/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 31 Jan 2024.

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

- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [On instabilities of deep learning in image reconstruction - Does AI come at a cost?](https://mlsanity.com/paper/1902.05300/) (2019)
- [Calibration in Deep Learning: A Survey of the State-of-the-Art](https://mlsanity.com/paper/2308.01222/) (2023)
- [Blessing of dimensionality: mathematical foundations of the statistical physics of data](https://mlsanity.com/paper/1801.03421/) (2018)
- [Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem](https://mlsanity.com/paper/2101.08286/) (2021)
- [Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation](https://mlsanity.com/paper/2112.07184/) (2021)
- [Correction of AI systems by linear discriminants: Probabilistic foundations](https://mlsanity.com/paper/1811.05321/) (2018)
- [The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks](https://mlsanity.com/paper/2109.06098/) (2021)
- [High-dimensional separability for one- and few-shot learning](https://mlsanity.com/paper/2106.15416/) (2021)
- [The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning](https://mlsanity.com/paper/2309.07072/) (2023)
- [One-Trial Correction of Legacy AI Systems and Stochastic Separation Theorems](https://mlsanity.com/paper/1610.00494/) (2016)
- [Learning from scarce information: using synthetic data to classify Roman fine ware pottery](https://mlsanity.com/paper/2107.01401/) (2021)

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

- [Agile gesture recognition for low-power applications: customisation for generalisation](https://mlsanity.com/paper/2403.15421/) (2024)

## Abstract (arXiv)

We present a new methodology for handling AI errors by introducing weakly supervised AI error correctors with a priori performance guarantees. These AI correctors are auxiliary maps whose role is to moderate the decisions of some previously constructed underlying classifier by either approving or rejecting its decisions. The rejection of a decision can be used as a signal to suggest abstaining from making a decision. A key technical focus of the work is in providing performance guarantees for these new AI correctors through bounds on the probabilities of incorrect decisions. These bounds are distribution agnostic and do not rely on assumptions on the data dimension. Our empirical example illustrates how the framework can be applied to improve the performance of an image classifier in a challenging real-world task where training data are scarce.