AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Globscope: Toward a Global View of the Loss Landscape

Mashiat Mustaq, Xavier M. Tricoche

CVPR 2026 · Architectures and efficiency › RNNs and normalization · approach: Symmetry and equivariance in loss landscapes

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 autoencoder instead of Kernel-PCA for the landscape embeddingGlobscope · ResNet56 CIFAR-10 landscapereconstruction loss (MSE): 0.004270 -> 0.000007Improved
use autoencoder instead of UMAP for the landscape embeddingGlobscope · ResNet56 CIFAR-10 landscapereconstruction loss (MSE): 0.501484 -> 0.000007Improved
project mode-connectivity curves onto the autoencoder landscapeGlobscope · ResNet56 CIFAR-10 mode connectivityloss along curve: MAE 0.006-0.016Improved
use autoencoder instead of Kernel-PCA for mode connectivity projectionGlobscope · ResNet56 CIFAR-10 mode connectivityqualitative basin separationImproved
use autoencoder instead of UMAP for mode connectivity projectionGlobscope · ResNet56 CIFAR-10 mode connectivityqualitative path coherenceImproved

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