Effect of Spherical Parameter Space on Number of Non-Forgetting Tasks and Capacity of Continual Learning

arXiv:2610.17453 · cs.LG, cs.IT, math.IT, stat.ML · Submitted 2026-10-12 · Read on arXiv

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

Submitted: 2026-10-12

Updated: 2026-10-12

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Continual Learning — 1× in this paper · explained in 3 episodes

Sources

• Subspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation
• Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting
• Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning
• Fisher-Orthogonal Projected Natural Gradient Descent for Continual Learning
• Towards guarantees for parameter isolation in continual learning

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