arXiv Machine Learning By Koen M. F. Gorgels, Lasai Barre\~nada, Maarten van Smeden, Ben Van Calster, Ewout W. Steyerberg, Wouter A. C. van Amsterdam

Optimizing for the decision not the prediction: an exploration of Smooth Net Benefit as a training objective

Read the original on arXiv Machine Learning →

The study introduces Smooth Net Benefit (σNB), a differentiable approximation of Net Benefit, as a training objective aimed at aligning predictive models with threshold‑specific clinical decisions. Experiments on the Framingham cardiovascular risk dataset and 44 TabZilla datasets show that σNB training yields modest improvements for logistic regression but little to no benefit for more flexible models such as GAMs and XGBoost. The authors conclude that σNB is not a universal replacement for negative log‑likelihood training, though it may be worth exploring in contexts where model flexibility is limited.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI
Aug 24

Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation

The paper investigates two strategies for improving large language model (LLM) evaluation: specialized judge weights and rule‑based deferral policies. Experiments on nearly 100,000 rubric‑conditioned samples show that correct rubrics boost accuracy, while incorrect ones hurt it, and that splitting training data into criterion‑specific experts can severely degrade performance unless the experts are warm‑started from a unified model. The authors demonstrate that lightweight deferral cascades can match or exceed the accuracy of larger standalone judges at a fraction of the compute cost, and they provide practical design rules for building efficient, reliable LLM evaluators.

By Ye Chen, Weining Zhang
arXiv Machine Learning
Sep 7

Mitra-v2 Technical Report

Mitra‑v2 is a tabular foundation model that achieves state‑of‑the‑art performance on a wide range of real‑world classification and regression tasks, including credit‑risk scoring, clinical prediction, equipment‑failure detection, and house‑price estimation. Trained solely on synthetic data with a larger and more diverse pretraining distribution than its predecessor, it uses a compact 2D Transformer backbone and improved optimization to handle longer contexts and larger feature spaces. On the TabArena and TALENT benchmarks, Mitra‑v2 outperforms leading models such as TabPFN‑3 and TabICLv2, matching the performance of a 1.6B‑parameter TabFM with only 77M parameters, and ranks first on multi‑class classification tasks with more than ten classes.

By Yefan Tao (Bernie), Xiyuan Zhang (Bernie), Xinyi Liu (Bernie), Boran Han (Bernie), Danielle Maddix (Bernie), Haoyang Fang (Bernie), Zhen Han (Bernie), Jiading Gai (Bernie), Xuanqing Liu (Bernie), Michael Bohlke-Schneider (Bernie), Yuyang (Bernie), Wang, Gerald Friedland, Kevan Mah, Chris Lee, Chris Kong
arXiv AI
Sep 3

The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinical Prediction

The paper introduces a framework that distinguishes two causes of saturation in clinical prediction: a learner gap, where the model fails to use available information, and a measurement‑channel ceiling, where the recorded variables limit performance. It provides theoretical characterizations, finite‑sample diagnostics, and empirical audits across three large cohorts, showing that well‑tuned models approach the frontier while deficient learners leave large gaps. A PRISMA‑guided synthesis across 104 tasks reveals consistent channel‑level patterns, suggesting that improving the learner or the measurement channel can audit and potentially lift performance.

By Sayeed Shafayet Chowdhury, Nusrat Jahan, Snehasis Mukhopadhyay, Shiaofen Fang, Vijay R. Ramakrishnan
arXiv Computation and Language
Sep 11

Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

The study audited ten different classifiers—including linear, tree‑ensemble, neural, glass‑box, and tabular foundation models—on national health survey data to predict myocardial infarction. By systematically removing features that could cause target leakage, the authors found that all models’ AUROC scores collapsed into a narrow band, indicating that reported high accuracy in prior work was largely due to leakage rather than model sophistication. The glass‑box explainable boosting machine performed comparably to other models while being much faster, and the authors demonstrated that fairness, calibration, and uncertainty can be audited and repaired without sacrificing performance.

By Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif, Samer Ellaham, Cedric Schmitz