Pith. sign in

REVIEW 2 cited by

On Quadratic Penalties in Elastic Weight Consolidation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1712.03847 v1 pith:VDHYIQMD submitted 2017-12-11 stat.ML cs.LG

classification stat.MLcs.LG
keywords consolidationderivationelastickirkpatrickpenaltiesquadratictasksweight
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Elastic weight consolidation (EWC, Kirkpatrick et al, 2017) is a novel algorithm designed to safeguard against catastrophic forgetting in neural networks. EWC can be seen as an approximation to Laplace propagation (Eskin et al, 2004), and this view is consistent with the motivation given by Kirkpatrick et al (2017). In this note, I present an extended derivation that covers the case when there are more than two tasks. I show that the quadratic penalties in EWC are inconsistent with this derivation and might lead to double-counting data from earlier tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning

    cs.LG 2025-02 conditional novelty 6.0 of 10

    OCAR combines experience replay with K-FAC Fisher preconditioning and scheduled damping to improve stability and plasticity in online continual learning.

  2. Act Now: A Novel Online Forecasting Framework for Large-Scale Streaming Data

    cs.LG 2024-11 conditional novelty 3.0 of 10

    Act-Now combines random subgraph sampling, fast and slow stream buffers, and a label-decomposition forecaster, reporting large MSE reductions on three cellular traffic datasets.

Pith tools