paper-with-me

홈 › Papers

Enhancing Automated Machine Learning via Homogeneous Train-Test Splitting Methods

2026-07-29 · Yearn Tan Yin Tze, Charles Grellois arxiv

Accurate model evaluation in machine learning depends critically on how datasets are split into training and testing subsets. Standard random splitting assumes that both partitions share the same underlying distribution, an assumption often violated in datasets with class imbalance, natural clustering, or spatial autocorrelation. This paper investigates the role of statistical similarity in train-test splitting and its consequences for AutoML model evaluation. Five established strategies are compared across fifteen UCI benchmark datasets: random splitting, stratified sampling, Kennard-Stone, Duplex, and SPXY. Similarity is assessed using chi-square, Kolmogorov-Smirnov, and Maximum Mean Discrepancy (MMD) tests. Geometry-based methods consistently produce near-zero MMD scores, introducing instability into downstream performance estimates. The proposed Optimised-Distribution method treats similarity as an explicit optimisation objective and achieves the highest mean MMD similarity, 89.0%, across all strategies evaluated.

📄 PDF Abstract BibTeX arXiv:2607.26625

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation

2025-09-30 · Wenda Xu, Sweta Agrawal, Vilém Zouhar, Markus Freitag 외 arxiv

As LLMs rapidly saturate existing benchmarks, automated benchmark creation using LLMs (LLM-as-a-benchmark) -- where a model generates test inputs (LLM-as-a-testset) and evaluates outputs (LLM-as-an-evaluator) -- has gain…

Machine Translation

A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive Testing

2024-05-26 · Yusaku Ando, Miya Nakajima, Takahiro Saitoh, Tsuyoshi Kato

In recent years, the deterioration of artificial materials used in structures has become a serious social issue, increasing the importance of inspections. Non-destructive testing is gaining increased demand due to its ca…

Anomaly DetectionDefect Detectionobject-detectionObject Detection+1

Rethinking Verification for LLM Code Generation: From Generation to Testing

2025-07-09 · Zihan Ma, Taolin Zhang, Maosong Cao, Junnan Liu 외

Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise o…

Code GenerationHumanEval

Markov Random Fields and Mass Spectra Discrimination

2014-10-13 · Ao Kong, Robert Azencott

For mass spectra acquired from cancer patients by MALDI or SELDI techniques, automated discrimination between cancer types or stages has often been implemented by machine learnings. These techniques typically generate "b…

Enhancing Deep Learning based RMT Data Inversion using Gaussian Random Field

2024-10-22 · Koustav Ghosal, Arun Singh, Samir Malakar, Shalivahan Srivastava 외

Deep learning (DL) methods have emerged as a powerful tool for the inversion of geophysical data. When applied to field data, these models often struggle without additional fine-tuning of the network. This is because the…

Deep Learning