# Benchmarking machine learning models for multi-class state recognition in double quantum dot data

arXiv: https://arxiv.org/abs/2511.22451 · HTML: https://mlsanity.com/paper/2511.22451/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 53 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction](https://mlsanity.com/paper/1906.03631/) (2019)
- [Rotation-invariant convolutional neural networks for galaxy morphology prediction](https://mlsanity.com/paper/1503.07077/) (2015)
- [Colloquium: Advances in automation of quantum dot devices control](https://mlsanity.com/paper/2112.09362/) (2021)
- [Tuning arrays with rays: Physics-informed tuning of quantum dot charge states](https://mlsanity.com/paper/2209.03837/) (2022)
- [Toward Robust Autotuning of Noisy Quantum Dot Devices](https://mlsanity.com/paper/2108.00043/) (2021)
- [Automated extraction of capacitive coupling for quantum dot systems](https://mlsanity.com/paper/2301.08654/) (2023)
- [A Mathematical Explanation of UNet](https://mlsanity.com/paper/2410.04434/) (2024)
- [A modular U-Net for automated segmentation of X-ray tomography images in composite materials](https://mlsanity.com/paper/2107.07468/) (2021)
- [Mixture Density Networks for Classification with an Application to Product Bundling](https://mlsanity.com/paper/2402.05428/) (2024)
- [Vision Transformers for End-to-End Quark-Gluon Jet Classification from Calorimeter Images](https://mlsanity.com/paper/2506.14934/) (2025)
- [QDFlow: A Python package for physics simulations of quantum dot devices](https://mlsanity.com/paper/2509.13298/) (2025)
- [Enhancing Rock Image Segmentation in Digital Rock Physics: A Fusion of Generative AI and State-of-the-Art Neural Networks](https://mlsanity.com/paper/2311.06079/) (2023)

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

- [Automated electrostatic characterization of quantum dot devices in single- and bilayer heterostructures](https://mlsanity.com/paper/2601.00067/) (2025)

## Abstract (arXiv)

Semiconductor quantum dots (QDs) are a leading platform for scalable quantum processors. However, scaling to large arrays requires reliable, automated tuning strategies for devices' bootstrapping, calibration, and operation, with many tuning aspects depending on accurately identifying QD device states from charge-stability diagrams (CSDs). In this work, we present a comprehensive benchmarking study of four modern machine learning (ML) architectures for multi-class state recognition in double-QD CSDs. We evaluate their performance across different data budgets and normalization schemes using both synthetic and experimental data. We find that the more resource-intensive models -- U-Nets and visual transformers (ViTs) -- achieve the highest MSE score (defined as 1-MSE) on synthetic data (over 0.98) but fail to generalize to experimental data. MDNs are the most computationally efficient and exhibit highly stable training, but with substantially lower peak performance. CNNs offer the most favorable trade-off on experimental CSDs, achieving strong accuracy with two orders of magnitude fewer parameters than the U-Nets and ViTs. Normalization plays a nontrivial role: min-max scaling generally yields higher MSE scores but less stable convergence, whereas z-score normalization produces more predictable training dynamics but at reduced accuracy for most models. Overall, our study shows that CNNs with min-max normalization are a practical approach for QD CSDs.