AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning

Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang

TPAMI 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 16 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
replace cross-entropy with EvoMAL lossResNet-18 · CIFAR-10error rate: 0.0658 -> 0.0528Improved
replace cross-entropy with EvoMAL lossLeNet-5 · MNISTerror rate: 0.0203 -> 0.0100Improved
replace squared error with EvoMAL lossMLP · California Housingtest MSE: 0.2326 -> 0.1723Improved
replace squared error with EvoMAL lossMLP · Boston Housingtest MSE: 0.1304 -> 0.1314No clear effect
replace cross-entropy with EvoMAL lossPyramidNet · CIFAR-100error rate: 0.2527 -> 0.2664Hurt
add gradient-based local search (unrolled differentiation) to genetic programming (ablation)EvoMAL · CIFAR-10 ResNet-18error rate: 0.0818 -> 0.0528Improved
add gradient-based local search (unrolled differentiation) to genetic programming (ablation)EvoMAL · CIFAR-100 WideResNeterror rate: 0.3382 -> 0.2276Improved
transfer EvoMAL loss learned on CIFAR-10 to CIFAR-100EvoMAL · CIFAR-100 AlexNet (transfer)error rate: 0.5262 -> 0.5324Hurt
transfer EvoMAL loss learned on CIFAR-10 to CIFAR-100EvoMAL · CIFAR-100 ResNet-18 (transfer)error rate: 0.2474 -> 0.2326Improved
use parametric neural-network loss (ML3) instead of symbolic loss for transferML3 · CIFAR-100 ResNet-18 (transfer)error rate: 0.2474 -> 0.6000Hurt
tune base learning rate for cross-entropy baseline and EvoMAL (ablation)EvoMAL · CIFAR-10 AllCNN-Cerror rateMixed

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