# On Hyperparameter Tuning on the Test Set

arXiv: https://arxiv.org/abs/2610.05902 · HTML: https://mlsanity.com/paper/2610.05902/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Do CIFAR-10 Classifiers Generalize to CIFAR-10?](https://mlsanity.com/paper/1806.00451/) (2018)
- [Troubling Trends in Machine Learning Scholarship](https://mlsanity.com/paper/1807.03341/) (2018)
- [Generalization in Adaptive Data Analysis and Holdout Reuse](https://mlsanity.com/paper/1506.02629/) (2015)
- [Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision](https://mlsanity.com/paper/2109.08203/) (2021)
- [Model Similarity Mitigates Test Set Overuse](https://mlsanity.com/paper/1905.12580/) (2019)
- [Scaling Down Deep Learning with MNIST-1D](https://mlsanity.com/paper/2011.14439/) (2020)
- [Importance of Tuning Hyperparameters of Machine Learning Algorithms](https://mlsanity.com/paper/2007.07588/) (2020)
- [Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification](https://mlsanity.com/paper/2108.13122/) (2021)
- [Overtuning in Hyperparameter Optimization](https://mlsanity.com/paper/2506.19540/) (2025)
- [Black Magic in Deep Learning: How Human Skill Impacts Network Training](https://mlsanity.com/paper/2008.05981/) (2020)
- [Efficient Hyperparameter Importance Assessment for CNNs](https://mlsanity.com/paper/2410.08920/) (2024)

## Abstract (arXiv)

"Don't tune hyperparameters on the test set" is often stated in machine learning textbooks. Violating it is considered a cardinal sin that produces misleadingly optimistic results, corrupts benchmark integrity, and thus can even be interpreted as scientific fraud. Yet evidence suggests that test set hyperparameter tuning does occur in practice, making it all the more important to understand its actual consequences. So how bad is it, really? In this work we question this dogma and put it to an empirical test. We systematically study the magnitude of the performance inflation caused by tuning the hyperparameters on the test set for MNIST-1D, CIFAR-10, and three tasks from the GLUE benchmark. Our experiments show that while the effect is real and significant, it is frequently small relative to other sources of noise. In many cases, we find that tuning on the test set recovers exactly the same model as when tuning on the validation set. Most importantly, we find that the rankings of models remain essentially preserved after tuning on the test set and therefore that consistent test-set tuning may not invalidate benchmarks or model selection. Our results call for a more nuanced view of tuning hyperparameters on the test set, stimulating researchers to openly report test tuning.