An Extreme Value Perspective on Learning Stress Laws
Mantu Gupta, Anand Deo
q-fin.RM, stat.ML
Submitted: 2026-07-12
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Tail-GAN: Learning to Simulate Tail Risk Scenarios
- Denoising Diffusion Probabilistic Models
- $t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
- Auto-Encoding Variational Bayes
- A VAE Approach to Sample Multivariate Extremes
- Heavy-Tailed Diffusion Models
- Copula & Marginal Flows: Disentangling the Marginal from its Joint
Related papers
- Financial Tail Risk Beyond Lipschitz Continuity via Semi-Discrete Optimal Transport
- DisclosureBeta: A Measurement-Channel Theory for Regime-Conditioned Betas from LLM-Read Risk Disclosures
- Pricing the DeFi Tail: Do Protocols or Depositors Price Operational Risk?
- On the approximation of posterior laws in compound loss models by conditional Wasserstein GANs
- DTD-VAE: Disentangled Temporal Dependencies VAE for Credit Risk Prediction
- Model Validation of Agentic AI Systems: A POMDP-Based Framework for Belief-State, Forecast, and Policy Validation