Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
Byrd, Peihuang Lu, Jorge Nocedal, and Ciyou Zhu
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
MERGE-RNA uses maximum-entropy modeling of the DMS probing pipeline to learn a small set of transferable parameters that predict RNA secondary structure ensembles matching experimental reactivity better than standard pseudo-free-energy approaches.
citing papers explorer
-
Form and Function: Machine Unlearning as a Problem of Misaligned States
Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
-
MERGE-RNA: a physics-based model to predict RNA secondary structure ensembles with chemical probing
MERGE-RNA uses maximum-entropy modeling of the DMS probing pipeline to learn a small set of transferable parameters that predict RNA secondary structure ensembles matching experimental reactivity better than standard pseudo-free-energy approaches.