AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Integrating Random Effects in Deep Neural Networks

Giora Simchoni, Saharon Rosset

JMLR 2023 · Optimization › Implicit bias and generalization · approach: Stability-based generalization analysis · 15 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
use LMMNN random-effects NLL instead of one-hot encodingDNN · Simulated single categorical feature, g(Z)=Z, sigma_b^2=10, q=10^4test MSE: 2.37 -> 1.29Improved
use LMMNN instead of entity embeddingsDNN · Simulated single categorical feature, g(Z)=Z, sigma_b^2=10, q=10^4test MSE: 2.12 -> 1.29Improved
use LMMNN instead of ignoring the categorical featureDNN · Simulated single categorical feature, g(Z)=Z, sigma_b^2=10, q=10^4test MSE: 11.2 -> 1.29Improved
use LMMNN instead of MeNetsDNN · Simulated single categorical feature, g(Z)=Z, sigma_b^2=10, q=10^4test MSE: 2.80 -> 1.29Improved
use LMMNN instead of lme4 LMMlinear mixed model · Simulated single categorical feature, g(Z)=Z, sigma_b^2=0.1, q=10^2test MSE: 2.93 -> 1.10Improved
use LMMNN instead of lme4 when g(Z) is nonlinear and q is largelme4 · Simulated single categorical feature, g(Z)=ZW, sigma_b^2=10, q=10^4test MSE: 13.8 -> 13.9No clear effect
use LMMNN instead of one-hot encoding with g(Z)=ZWDNN · Simulated single categorical feature, g(Z)=ZW, sigma_b^2=10, q=10^4test MSE: 81.3 -> 13.9Improved
use LMMNN instead of OHE with three categorical featuresDNN · Simulated 3 categorical features, g(Z)=Z, sigma_b^2=(0.3,0.3,0.3)test MSE: 1.62 -> 1.16Improved
use LMMNN instead of LSTM for longitudinal dataDNN · Simulated longitudinal, Random mode, q=10^4test MSE: 1.40 -> 1.23Improved
use known RBF kernel random field (LMMNN-R) instead of learned embedding of locations (LMMNN-E)LMMNN · Simulated spatial RBF, sigma_b0^2=10, sigma_b1^2=0.1, q=10^4test MSE: 2.92 -> 1.57Improved
use LMMNN-R instead of SVDKLDNN · Simulated spatial RBF, sigma_b0^2=10, sigma_b1^2=0.1, q=10^4test MSE: 2.38 -> 1.57Improved
use LMMNN-R instead of SVDKL in typical spatial scenariosDNN · Simulated spatial RBF, sigma_b0^2=0.1, sigma_b1^2=0.1, q=10^2test MSE: 1.09 -> 1.10No 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