AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvalues

Jakob Kramp, Javed Lindner, Moritz Helias

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 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
increase Langevin noise temperature (larger 2/beta) (ablation)random feature regression with power-law spectrum · teacher-student simulation, P=N=100test errorHurt
train longer under noise (no early stopping) (ablation)Langevin regression dynamics · teacher-student simulationtest errorHurt
add early stopping at t* = (beta/2) * alpha/(1+alpha)Langevin regression dynamics · noisy trainingtest errorImproved
increase L2 regularization 1/(g beta) (ablation)Langevin regression dynamics · high fixed noise, P=N=100test error at long timesImproved
increase L2 regularization 1/(g beta) (ablation)Langevin regression dynamics · high fixed noise, P=N=100minimum test error and its locationNo clear effect
increase number of training samples P (ablation)Langevin regression dynamics · power-law spectrumbias and variance error: bias ~ (Pt)^(-alpha/(1+alpha)); variance ~ P^(-alpha/(1+alpha))Improved
vary P and N in optimal stopping time (ablation)optimal stopping time t* · P=N=100 simulationoptimal stopping timeNo 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