AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Towards Understanding Grokking: An Effective Theory of Representation Learning

Ziming Liu, Ouail Kitouni, Niklas Nolte, Eric J Michaud, Max Tegmark, Mike Williams

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 24 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 weight decay to the decoder only (ablation)transformer on modular addition (p=53) · modular additiongeneralization speedImproved
Add dropout in the decoder blocks (ablation)transformer on modular addition (p=53) · modular additionsteps to generalize: under 10^3 stepsImproved
Add decoder weight decay (ablation)toy encoder-decoder model · toy additiongeneralization phaseMixed
Make representation learning faster relative to the decoder (ablation)toy encoder-decoder model · toy additiongeneralization phaseImproved
Increase training data fraction above critical valuetoy addition model · toy addition (p=10)grokking steps: critical fraction 0.4Improved

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