Formalizing Forgetting: Theory of Forgetting for Online Continual Learning

arXiv:2610.14787 · cs.LG · Submitted 2026-10-10 · Read on arXiv

cs.LG

Submitted: 2026-10-10

Updated: 2026-10-10

Terminology

• Continual Learning — 1× in this paper · explained in 2 episodes

Sources

• Improving information retention in large scale online continual learning
• AIR: Analytic Imbalance Rectifier for Continual Learning
• Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives
• The impact of model size on catastrophic forgetting in Online Continual Learning
• Replay Can Provably Increase Forgetting
• Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance

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