Research map / Architectures and efficiency / RNNs and normalization
Globscope: Toward a Global View of the Loss Landscape
Mashiat Mustaq, Xavier M. Tricoche
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use autoencoder instead of Kernel-PCA for the landscape embedding | Globscope · ResNet56 CIFAR-10 landscape | reconstruction loss (MSE): 0.004270 -> 0.000007 | Improved |
| use autoencoder instead of UMAP for the landscape embedding | Globscope · ResNet56 CIFAR-10 landscape | reconstruction loss (MSE): 0.501484 -> 0.000007 | Improved |
| project mode-connectivity curves onto the autoencoder landscape | Globscope · ResNet56 CIFAR-10 mode connectivity | loss along curve: MAE 0.006-0.016 | Improved |
| use autoencoder instead of Kernel-PCA for mode connectivity projection | Globscope · ResNet56 CIFAR-10 mode connectivity | qualitative basin separation | Improved |
| use autoencoder instead of UMAP for mode connectivity projection | Globscope · ResNet56 CIFAR-10 mode connectivity | qualitative path coherence | Improved |
Closest papers by meaning
- Taxonomizing local versus global structure in neural network loss landscapes (NeurIPS 2021 · similarity 0.90)
- Generalized Linear Mode Connectivity for Transformers (NeurIPS 2025 · similarity 0.87)
- Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine Learning (ICML 2024 · similarity 0.86)
- Flat Channels to Infinity in Neural Loss Landscapes (NeurIPS 2025 · similarity 0.85)
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.85)
- Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime (ICML 2025 · similarity 0.85)
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.
