Introduces COLD, a DPP-based continual learning framework with stability and convergence guarantees that outperforms prior methods on benchmarks via tunable stability-plasticity control.
Projection-free algorithms for online convex optimization with adversarial constraints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Theoretical Foundations of Continual Learning via Drift-Plus-Penalty
Introduces COLD, a DPP-based continual learning framework with stability and convergence guarantees that outperforms prior methods on benchmarks via tunable stability-plasticity control.