PMF-CL derives Pareto-optimal solutions for continual learning on conflicting tasks, yielding memory-efficient algorithms for linear regression and quadratically bounded losses with static O(d^2) memory.
Lemma E.1(Böhning (1992)).For a probability vector p∈∆ K−1, the matrix V(p) := Diag(p)− pp⊤ is upper bounded by: V:= 1 2 I K − 1 K 11⊤ ,(63) where1is the all-ones vector of sizeK
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
-
PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks
PMF-CL derives Pareto-optimal solutions for continual learning on conflicting tasks, yielding memory-efficient algorithms for linear regression and quadratically bounded losses with static O(d^2) memory.