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.
Information-theoretic Online Memory Selection for Continual Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A challenging problem in task-free continual learning is the online selection of a representative replay memory from data streams. In this work, we investigate the online memory selection problem from an information-theoretic perspective. To gather the most information, we propose the \textit{surprise} and the \textit{learnability} criteria to pick informative points and to avoid outliers. We present a Bayesian model to compute the criteria efficiently by exploiting rank-one matrix structures. We demonstrate that these criteria encourage selecting informative points in a greedy algorithm for online memory selection. Furthermore, by identifying the importance of \textit{the timing to update the memory}, we introduce a stochastic information-theoretic reservoir sampler (InfoRS), which conducts sampling among selective points with high information. Compared to reservoir sampling, InfoRS demonstrates improved robustness against data imbalance. Finally, empirical performances over continual learning benchmarks manifest its efficiency and efficacy.
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.