AI Paper Atlas

Research map / Continual learning / Online and replay-based

Continual Learning through Control Minimization

Sander de Haan, Yassine Taoudi-Benchekroun, Pau Vilimelis Aceituno, Benjamin F Grewe

ICML 2026 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use EFC control-minimization instead of oEWCregularization-based continual learning · Split-CIFAR10 (Class-IL)accuracy (%): 21.2 -> 50.2Improved
use EFC instead of EWCSplit-MNIST MLP · Split-MNIST (Class-IL)accuracy (%): 19.8 -> 51.4Improved
use EFC instead of oEWCSplit-Tiny-ImageNet · Split-Tiny-ImageNet (Class-IL)accuracy (%): 4.8 -> 8.8Improved
use EFC instead of oEWC in task-incremental learningSplit-MNIST · Split-MNIST (Task-IL)accuracy (%): 99.2 -> 98.3No clear effect
use EFC instead of EWC in task-incremental learningSplit-CIFAR10 · Split-CIFAR10 (Task-IL)accuracy (%): 95.5 -> 96.2No clear effect
add replay (DER++, buffer 200) rather than EFCSplit-MNIST class-IL · Split-MNIST (Class-IL)accuracy (%): 51.4 -> 71.1Improved
replace diagonal Fisher (EWC) with full Fisher (FISH) in regularizationEWC on two-task Split-MNIST · Split-MNIST two-task class-IL (MLP 64x2)Task-A forgettingImproved
use EFC instead of full-Fisher FISHtwo-task Split-MNIST · Split-MNIST two-task class-IL (MLP 64x2)Task-A accuracy decreaseImproved
improve curvature approximation (diagonal to full Fisher) in backprop regularizationclass-incremental learning · Split-MNIST two-task class-IL (MLP 64x2)class-IL loss convergenceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy