A nested-projection gradient algorithm attains O(log T) regret with O(log T) cumulative constraint violation for strongly convex losses, and O(√T) for both with convex losses; the body's proof is coherent, though the abstract claims lower-bound results the body never contains.
o( √ T ) static regret and instance dependent constraint violation for con- strained online convex optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 2years
2026 2roles
other 1polarities
unclear 1representative citing papers
Introduces COLD, a DPP-based continual learning framework with stability and convergence guarantees that outperforms prior methods on benchmarks via tunable stability-plasticity control.
citing papers explorer
-
A Geometric Approach to Constrained Online Learning
A nested-projection gradient algorithm attains O(log T) regret with O(log T) cumulative constraint violation for strongly convex losses, and O(√T) for both with convex losses; the body's proof is coherent, though the abstract claims lower-bound results the body never contains.
-
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.