A layer-wise information-theoretic decomposition bounds replay-based continual learning's generalization gap, predicting memory scaling, an interior stabilization layer, and gradient-alignment signals that track forgetting.
Catastrophic interference in connectionist networks: The sequential learning problem,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
A layer-wise information-theoretic decomposition bounds replay-based continual learning's generalization gap, predicting memory scaling, an interior stabilization layer, and gradient-alignment signals that track forgetting.