AI Paper Atlas

Research map / Continual learning / Online and replay-based

Asymptotic analysis of shallow and deep forgetting in replay with neural collapse

Giulia Lanzillotta, Damiano Meier, Thomas Hofmann

ICLR 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
add a small replay buffer (about 5%)Experience Replay · CIFAR100, ResNetdeep forgettingImproved
increase replay buffer toward 100%Experience Replay · CIFAR100, ResNetshallow forgettingImproved
initialize new heads with norm matched to previous heads (ablation)Experience Replay (CIL/TIL) · CIFAR100forgetting and test accuracyNo clear effect
reduce feature dimension to 10 (bottleneck regime) (ablation)Experience Replay · CIFAR100, ResNet, 5% replayshallow vs deep forgetting gap: 52.27 -> 26.15No 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