Extreme Value Theory

Follow this topic Ask about this topic

Extreme Value Theory studies the behavior of unusually large or small observations, helping estimate rare-event probabilities and extreme quantiles when data are scarce. Common approaches model threshold exceedances or block maxima, estimate tail shape, and account for dependence; newer work combines these tools with boosting, kernel methods, generative models, and causal inference. Applications include insurance losses, communications, spatial systems, and safety-critical prediction. A central challenge is that tail estimates can be sensitive to modeling assumptions and threshold choices, so reliable extrapolation needs diagnostics and should sometimes be withheld when the data provide too little support.

Latest papers

12 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Deep catastrophic-risk-aware reinforcement learning
Oct 19, 2026Carlos Pérez Octavio Mendoza, Frédéric GodinRisk-Sensitive RL Conditional Value-at-Risk
Concordia University, Department of Mathematics and Statistics, Montréal, Canada · Quantact Laboratory, Centre de Recherches Mathématiques, Montréal, Canada
A Location-Invariant Estimator of Extremal Quantile Treatment Effects for Heavy-Tailed Distributions
Sep 3, 2026Xin Yu, Shuwei Huang, Jicheng Liu +4Causal Effect Estimation Heavy-Tailed Distributions
Huazhong University of Science and Technology · Tencent
Physics-informed VAE-EVT for Tail Aware Radio Map Prediction
Aug 15, 2026Amanda Sheron Gamage, Niloofar Mehrnia, James GrossRadio Propagation Modeling Wireless Communications
Department of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Sweden
Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives
Jun 15, 2026Luca ZhouLLM Evaluation Language Model Safety Evaluation
Sapienza University of Rome
Gradient boosting for extremes: sampling theory and application to insurance
Jun 12, 2026Stéphane Lhaut, Olivier LopezGradient-Boosted Decision Trees Heavy-Tailed Distributions
1CREST, CNRS, Ecole polytechnique, Groupe ENSAE-ENSAI, ENSAE Paris, Institut Polytechnique de Paris, Palaiseau, France
Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach
May 29, 2026Baptiste Leroux, Clément Dombry, Anne SabourinQuantile Regression OOD Generalization
Université Paris Cité, CNRS, MAP5, F-75006 Paris, France · Université Marie et Louis Pasteur, CNRS, LmB (UMR 6623), F-25000 Besançon, France · Université Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, F-75006, Paris, France
When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
May 29, 2026Melihcan Erol, Suat Evren, Oktay Ozel +3Contrastive Learning Representation Learning
Massachusetts Insititute of Technology, Cambridge, Massachusetts · Boston University, Boston, Massachusetts.
Stop Suppressing the Tail: Causal Inference for Extreme Events
May 26, 2026Eichi UeharaCausal Effect Estimation Causal Inference
Extrapolation in Statistical Learning with Extreme Value Theory
May 3, 2026Sebastian Engelke, Nicola Gnecco, Anne SabourinOOD Generalization Statistical Learning Theory
Research Institute for Statistics and Information Science, University of Geneva, Switzerland · Department of Mathematics, Imperial College London, United Kingdom · Université Paris Cité, Université Paris-Saclay, ENS Paris-Saclay, CNRS, SSA, INSERM, Centre Borelli, France
SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination
Apr 30, 2026Eichi UeharaDouble ML Robust Regression
Independent researcher.
EVT-Based Generative AI for Tail-Aware Channel Estimation
Apr 27, 2026Parmida Valiahdi, Niloofar Mehrnia, Walid Saad +1Synthetic Data Augmentation Wireless Communications
∗Department of Electrical and Electronics Engineering, Koc University, Istanbul, Turkey · †Department of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden · ‡Department of Electrical and Computer Engineering, Virginia Tech, Virginia, United States
Multi-output Extreme Spatial Model for Complex Aircraft Production Systems
Apr 24, 2026Cheolhei Lee, Xing Wang, Xiaowei Yue +1Extreme Value Theory
Grado Department of Industrial and Systems Engineering, Virginia Polytechnic Institute and State University, Blacksburg, Virginia 24061 · Department of Mathematics, Illinois State University, Normal, Illinois 61790 · Department of Industrial Engineering, Tsinghua University, Beijing, 100084 China +1

Oct 19, 2026J/K move · Enter open · S save

Deep catastrophic-risk-aware reinforcement learning

Carlos Pérez Octavio Mendoza, Frédéric Godin

Concordia University, Department of Mathematics and Statistics, Montréal, Canada · Quantact Laboratory, Centre de Recherches Mathématiques, Montréal, Canada

Risk-Sensitive RL Conditional Value-at-Risk Extreme Value Theory Quantitative Finance

Open paper AskPDF arXiv

Estimating extreme risk in reinforcement learning becomes increasingly difficult as the confidence level increases, since only a small number of observations contribute to empirical estimates of Conditional Value-at-Risk (CVaR). In this paper, we extend an Extreme Value Theory (EVT) approach for CVaR optimization to high-dimensional neural-network policies. Using a peaks-over-threshold representation and method-of-moments estimation, we obtain a differentiable tail-risk objective and show that, conditional on the selected threshold, its finite-sample gradient can be computed directly through automatic differentiation. We first validate the approach in a controlled experiment with a known optimal solution and then investigate its performance in a deep-hedging problem with rare extreme market movements. Our results show similar hedging behavior for EVT- and empirical-CVaR-trained policies under normal conditions, while EVT-trained policies exhibit lower hedging losses under the extreme-scenario evaluation across the training sample sizes considered. These results suggest that EVT can provide a practical alternative for training neural policies when the observations relevant to extreme risk are scarce.