paper-with-me

Papers

Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well

2026-06-10 · Célestin Eve, Gaël Varoquaux, Thomas Moreau arxiv

Modern machine learning progresses through empirical work, benchmarking new methods to evaluate relative performance. However, the statistical variability inherent to evaluation - exacerbated by the stochastic nature of many algorithms - often makes performance estimation unreliable due to the limited test samples available, leading to a validation crisis in which genuine advances are difficult to discern. In this work, we show that cross-validation improves markedly confidence when evaluating and comparing learning algorithm performances. We introduce the concept of sample gain, which quantifies the virtual data augmentation achieved by using multiple cross-validation splits to reduce benchmarking variance. Experiments on both synthetic and real-world datasets (histopathologic scans and NLP fine-tuning) demonstrate that multiple splits can substantially improve the reliability and stability of performance estimates, with diminishing returns often setting in later than expected. We also introduce a procedure to dynamically early-stop cross-validation by estimating from the first few folds if subsequent folds will bring large sample gains. Our findings highlight the value of pushing cross-validation on available samples to achieve robust and reliable benchmarking.

📄 PDF Abstract BibTeX arXiv:2606.12552

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

What is Reproducibility in Artificial Intelligence and Machine Learning Research?

2024-04-29 · Abhyuday Desai, Mohamed Abdelhamid, Nakul R. Padalkar

In the rapidly evolving fields of Artificial Intelligence (AI) and Machine Learning (ML), the reproducibility crisis underscores the urgent need for clear validation methodologies to maintain scientific integrity and enc…

Enumerating the k-fold configurations in multi-class classification problems

2024-01-24 · Attila Fazekas, Gyorgy Kovacs

K-fold cross-validation is a widely used tool for assessing classifier performance. The reproducibility crisis faced by artificial intelligence partly results from the irreproducibility of reported k-fold cross-validatio…

Binary ClassificationMulti-class Classification

A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference

2026-01-02 · Qingwen Pu, Kun Xie, Hong Yang, Guocong Zhai arxiv

Existing paradigms for inferring pedestrian crossing behavior, ranging from statistical models to supervised learning methods, demonstrate limited generalizability and perform inadequately on new sites. Recent advances i…

Few-Shot Learning

No crisis should go to waste

2016-11-28

The crisis in the reproducibility of experiments invites a re-evaluation of methods of inquiry and validation procedures. The text challenges current assumptions of knowledge acquisition and introduces G-complexity for d…

ExplainGAN: Model Explanation via Decision Boundary Crossing Transformations

2018-09-01 · ECCV 2018 9 · Pouya Samangouei, Ardavan Saeedi, Liam Nakagawa, Nathan Silberman

We introduce a new method for interpreting computer vision models: visually perceptible, decision-boundary crossing transformations. Our goal is to answer a simple question: why did a model classify an image as being of …

model