Why Forget-Only Unlearning Needs Memorization

arXiv:2610.10519 · cs.LG, cs.IT, math.IT, stat.ML · Submitted 2026-10-07 · Read on arXiv

cs.LG, cs.IT, math.IT, stat.ML

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Machine Unlearning — 15× in this paper · explained in 2 episodes
• Approximate Unlearning — 4× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• In International Conference on Machine Learning — 2× in this paper
• Matrix Completion — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Differential Privacy — 1× in this paper · explained in 4 episodes
• In Conference on Learning Theory — 1× in this paper
• In International Conference on Learning Representations — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Who's Harry Potter? Approximate Unlearning in LLMs
• An Information Theoretic Approach to Machine Unlearning
• Less Noise, Same Certificate: Retain Sensitivity for Unlearning
• On the Impossibility of Retrain Equivalence in Machine Unlearning

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks