arXiv Machine Learning August 13, 2026 By Tieliang Gong, Zhongbo Zhang, Wen Wen, Yong-Jin Liu

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

Read the original on arXiv Machine Learning →

arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 9

Theoretical Foundations of Continual Learning via Drift-Plus-Penalty

arXiv:2606. 08452v1 Announce Type: new Abstract: In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch.

By Nazreen Shah, Govinda Arya, Bharath B. N., Ranjitha Prasad

benchmarks

arXiv Machine Learning

1d ago

Geometry of Forgetting: Representation Flux in Continual Learning

arXiv:2608. 15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks.

By Maksim A. Kazanskii

benchmarks

arXiv Machine Learning

1d ago

Metaplasticity as adaptive gradient preconditioning for incremental learning

arXiv:2608. 14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses.

By Isabelle Aguilar, Zayn Andre Zainal, Omid Kavehei

benchmarks

arXiv Machine Learning

Jun 5

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

arXiv:2606. 06032v1 Announce Type: new Abstract: Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning.

By Ayushman Trivedi, Bhavika Melwani

arXiv Machine Learning

Jun 2

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning

arXiv:2606. 01379v1 Announce Type: new Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored.

By Anushka Tiwari, Kaiyi Ji

llms benchmarks

arXiv AI

Jul 13

Interference and Retention in Continual Learning

arXiv:2607. 09202v1 Announce Type: cross Abstract: Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation.

By Julius St\"ork

efficiency benchmarks

Related stories

Theoretical Foundations of Continual Learning via Drift-Plus-Penalty

Geometry of Forgetting: Representation Flux in Continual Learning

Metaplasticity as adaptive gradient preconditioning for incremental learning

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning

Interference and Retention in Continual Learning