AI Paper Atlas

Research map / Optimization / Optimizers

Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks

Dong-Young Lim, Sotirios Sabanis

JMLR 2024 · Optimization › Optimizers · approach: Second-order and structured preconditioning

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 boosting function (finite epsilon) (ablation)TheoPouLa · CIFAR-10 VGG11test accuracy: 91.48 -> 92.30Improved
add boosting function (finite epsilon) (ablation)TheoPouLa · CIFAR-10 ResNet34test accuracy: 94.31 -> 95.43Improved
add boosting function (finite epsilon) (ablation)TheoPouLa · CIFAR-10 DenseNet121test accuracy: 94.22 -> 95.66Improved
add boosting function (finite epsilon) (ablation)TheoPouLa · CIFAR-100 VGG11test accuracy: 68.11 -> 70.31Improved
add boosting function (finite epsilon) (ablation)TheoPouLa · CIFAR-100 ResNet34test accuracy: 75.91 -> 77.60Improved
add boosting function (finite epsilon) (ablation)TheoPouLa · CIFAR-100 DenseNet121test accuracy: 77.99 -> 79.90Improved
lambda 0.5 instead of 0.1 (too large step) (ablation)TheoPouLa · CIFAR-100 ResNet34test accuracy: 74.02 -> 1.90Hurt
lambda 0.01 instead of 0.1 (ablation)TheoPouLa · CIFAR-10 VGG11test accuracy: 92.14 -> 89.89Hurt
epsilon 0.001 instead of 0.1 (ablation)TheoPouLa · CIFAR-10 VGG11test accuracy: 92.14 -> 26.03Hurt
epsilon 1 instead of 0.1 (ablation)TheoPouLa · CIFAR-100 VGG11test accuracy: 70.57 -> 68.75Hurt
inverse temperature beta 10^4 instead of 10^10 (ablation)TheoPouLa · CIFAR-100 VGG11test accuracy: 70.16 -> 20.69Hurt
inverse temperature beta 10^8 vs 10^12 (ablation)TheoPouLa · CIFAR-10 ResNet34test accuracy: 95.42 -> 95.43No 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