# Data Twinning

arXiv: https://arxiv.org/abs/2110.02927 · HTML: https://mlsanity.com/paper/2110.02927/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 4 of 4)

- [Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)](https://mlsanity.com/paper/1610.02455/) (2016)
- [Support points](https://mlsanity.com/paper/1609.01811/) (2016)
- [SPlit: An Optimal Method for Data Splitting](https://mlsanity.com/paper/2012.10945/) (2020)
- [Information-Based Optimal Subdata Selection for Big Data Linear Regression](https://mlsanity.com/paper/1710.10382/) (2017)

## Built on by (most cited first, 10 of 10)

- [Optimal Ratio for Data Splitting](https://mlsanity.com/paper/2202.03326/) (2022)
- [Risk-Aware Control and Optimization for High-Renewable Power Grids](https://mlsanity.com/paper/2204.00950/) (2022)
- [A Global-Local Approximation Framework for Large-Scale Gaussian Process Modeling](https://mlsanity.com/paper/2305.10158/) (2023)
- [Band-gap regression with architecture-optimized message-passing neural networks](https://mlsanity.com/paper/2309.06348/) (2023)
- [Statistical process monitoring of artificial neural networks](https://mlsanity.com/paper/2209.07436/) (2022)
- [Surgical Phase and Instrument Recognition: How to identify appropriate Dataset Splits](https://mlsanity.com/paper/2306.16879/) (2023)
- [Density-Aware Farthest Point Sampling](https://mlsanity.com/paper/2509.13213/) (2025)
- [A model-free subdata selection method for classification](https://mlsanity.com/paper/2404.19127/) (2024)
- [Double Machine Learning for Adaptive Causal Representation in High-Dimensional Data](https://mlsanity.com/paper/2411.14665/) (2024)
- [Starting Off on the Wrong Foot: Pitfalls in Data Preparation](https://mlsanity.com/paper/2603.18190/) (2026)

## Abstract (arXiv)

In this work, we develop a method named Twinning, for partitioning a dataset into statistically similar twin sets. Twinning is based on SPlit, a recently proposed model-independent method for optimally splitting a dataset into training and testing sets. Twinning is orders of magnitude faster than the SPlit algorithm, which makes it applicable to Big Data problems such as data compression. Twinning can also be used for generating multiple splits of a given dataset to aid divide-and-conquer procedures and k-fold cross validation.