One-Step Curvature Probes Miss the Fitting Operator: Retained Capacity and Terminal Null-Space Correction for Continual Learning
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex Losses
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Machine Unlearning via Information Theoretic Regularization
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