FDR Control

FDR: False Discovery Rate

False discovery rate control studies how to select statistically supported findings while limiting the expected proportion of selections that are false. Classical procedures such as Benjamini–Hochberg are joined by knockoff filters, conformal p-values, e-values, and data-splitting methods, which can account for structured or dependent hypotheses. Recent work applies these tools to feature selection, anomaly and out-of-distribution detection, scientific discovery, and sequential or adaptive decisions. A central challenge is preserving reliable guarantees under dependence, model misspecification, or repeated selection without making procedures so conservative that they miss useful discoveries.

Latest papers

42 papers9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform'
May 13, 2026Oliver Hennhöfer, Maximilian Kirsch, Christine PreisachFDR Control Conformal Prediction
Intelligent Systems Research Group, Karlsruhe University of Applied Sciences
A Regret Perspective on Online Multiple Testing
May 13, 2026Qingyang Hao, Kongchang Zhou, Fang Kong +1FDR Control Regret Minimization
Southern University of Science and Technology
Decentralized Conformal Novelty Detection via Quantized Model Exchange
May 7, 2026Kyle Loh, Yu XiangFDR Control Conformal Prediction
Department of Mathematics and Statistics · Florida Atlantic University · Boca Raton, Florida
Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables
Apr 13, 2026Meiyi Zhu, Osvaldo SimeoneFDR Control E-Values
Department of Engineering, King’s College London, WC2R 2LS, London, U.K. · Institute for Intelligent Networked Systems, Northeastern University London, E1 8PH London, U.K.
Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection
Mar 12, 2026Abhinaba Basu, Pavan ChakrabortyLarge Language Model-Guided Scientific Discovery FDR Control
Indian Institute of Information Technology Allahabad (IIITA) and National Institute of Electronics & Information Technology (NIELIT). · Indian Institute of Information Technology Allahabad (IIITA).
Beyond False Discovery Rate: A Stepdown Group SLOPE Approach for Grouped Variable Selection
Mar 1, 2026Xuelin Zhang, Jingxuan Liang, Xinyue Liu +2Feature Selection FDR Control
College of Informatics, Huazhong Agricultural University, Wuhan, 430070, Hubei Province, China.
Empirically Calibrated Conditional Independence Tests
Feb 24, 2026Milleno Pan, Antoine de Mathelin, Wesley TanseyConditional Independence Testing Statistical Hypothesis Testing
Computational Oncology Memorial Sloan Kettering Cancer Center
Synthetic-Powered Multiple Testing with FDR Control
Feb 18, 2026Yonghoon Lee, Meshi Bashari, Edgar Dobriban +1Multiple Hypothesis Testing FDR Control
Department of Statistics and Data Science, The Wharton School, University of Pennsylvania, USA · Department of Electrical and Computer Engineering, Technion IIT, Israel · Department of Computer Science, Technion IIT, Israel
Provable FDR Control for Deep Feature Selection: Deep MLPs and Beyond
Dec 4, 2025Kazuma SawayaFDR Control Feature Selection
The University of Tokyo, Bunkyo, Tokyo, Japan
Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecture
Nov 10, 2025Karen SargsyanFDR Control Formal Verification
aInstitute of Chemistry, Academia Sinica, Taipei, Taiwan
Optimized Conformal Selection: Powerful Selective Inference After Data-Dependent Score Construction
Nov 27, 2024Tian Bai, Ying JinConformal Prediction Selective Inference
Department of Mathematics and Statistics, McGill University · Data Science Initiative and Department of Health Care Policy, Harvard University
Multiple Testing of Linear Forms for Noisy Matrix Completion
Dec 1, 2023Wanteng Ma, Lilun Du, Dong Xia +1FDR Control Matrix Completion
Department of Statistics and Data Science, University of Pennsylvania, USA · Department of Decision Analytics and Operations, City University of Hong Kong, Hong Kong · Department of Mathematics, Hong Kong University of Science and Technology, Hong Kong +1

May 13, 2026J/K move · Enter open · S save

Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform'

Oliver Hennhöfer, Maximilian Kirsch, Christine Preisach

Intelligent Systems Research Group, Karlsruhe University of Applied Sciences

FDR Control Conformal Prediction Anomaly Detection

Open paper AskPDF arXiv

Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without clear statistical interpretation. Conformal anomaly detection addresses this limitation by converting anomaly scores into calibrated p-values that are valid under the statistical assumption of data exchangeability, with a growing literature extending this idea beyond that setting. We present 'nonconform', a Python package for applying conformal anomaly detection within existing machine-learning workflows, and use it as the basis for an implementation-grounded introduction to the field. The package integrates with 'scikit-learn', 'pyod', and custom anomaly detectors, and provides a unified interface for calibration, p-value generation, and false discovery rate control. It supports several conformalization strategies, ranging from simple split-conformal calibration to more data-efficient and shift-aware extensions. Through a progression from foundational concepts to advanced conformalization strategies, complemented by code examples, the paper connects the statistical ideas behind conformal anomaly detection to their practical use in 'nonconform'. Empirical results demonstrate that the implemented methods enable statistically principled anomaly detection. Together, the package and exposition aim to make core conformal anomaly detection workflows more accessible and reproducible in experimental and production-oriented settings.