How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds
cs.LG
Submitted: 2026-09-23
Updated: 2026-09-23
Sources
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
- Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with nonconform
- Between Resolution Collapse and Variance Inflation: Weighted Conformal Anomaly Detection in Low-Data Regimes
- Adversarially Robust Few-Shot Anomaly Detection with Vision Foundation Models
- HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks
- SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
- Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks