AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity

Noa Rubin, Orit Davidovich, Zohar Ringel

ICLR 2026 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 6 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
allow GP-to-specialization feature learning in layer 2 instead of lazy GP-GPthree-layer erf FCN (Hermite-3 target) · predicted sample complexity scalevariational energy: d^3 -> sqrt(N_2 d)Improved
use specialization-magnetization pattern instead of GP-GPthree-layer erf FCN (Hermite-3 target) · predicted sample complexity scalevariational energy: d^3 -> (N_1 N_2 d)^{1/3}Improved
increase first-layer width N_1 (specialization-magnetization vs GP-specialization)three-layer erf FCN · sample complexityP_*: N_1^{1/3} vs no N_1 dependenceMixed
specialization pattern instead of GP in softmax attention headsoftmax attention (cubic target) · predicted sample complexityvariational energy: L d^3 -> sqrt(H L d^3)Improved
two-layer FCN with Hermite-3 target, proportional limittwo-layer erf FCN · sample complexity scaling in dP_*: P_* = dImproved

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