Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/jose-melo/kernel-contractionmatching
Terminology
Sources
- Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detection
- Interpretable Tabular Foundation Models via In-Context Kernel Regression
- GradStop: Exploring Training Dynamics in Unsupervised Outlier Detection through Gradient
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