AI Paper Atlas

Research map / Continual learning / Online and replay-based

The Ideal Continual Learner: An Agent That Never Forgets

Liangzu Peng, Paris Giampouras, Rene Vidal

ICML 2023 · 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
define the Ideal Continual Learner that jointly satisfies all task constraintsICL · theoryforgettingImproved
rehearsal with a stored subset of previous dataICL / rehearsal · theorygeneralization guaranteeImproved
increase network widthICL-dagger / deep continual learning · theorycatastrophic forgettingImproved
view multitask learning as the ICL special caseICL · theorycontinual learning performanceImproved
choose representative or diverse samples versus random for rehearsal memorymemory selection · text classification and QA (cited study)performanceNo clear effect
domain-incremental learning without architecture changeICL · theoryforgettingMixed

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