Research map / Optimization / Implicit bias and generalization
Essentially No Barriers in Neural Network Energy Landscape
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Connect independently trained minima with AutoNEB paths | Deep networks on CIFAR10 · CIFAR10 | Train energy: 0.0005 -> 0.0026 | No clear effect |
| Connect independently trained minima with AutoNEB paths | Deep networks on CIFAR100 · CIFAR100 | Test energy: 1.12 -> 1.13 | No clear effect |
| Connect independently trained minima with AutoNEB paths | Deep networks on CIFAR10 · CIFAR10 | Test error rate [%]: 4.9 -> 5.1 | Hurt |
| Connect independently trained minima with AutoNEB paths | Deep networks on CIFAR100 · CIFAR100 | Test error rate [%]: 23.7 -> 24.6 | Hurt |
| Increase network depth and width | CNNs on CIFAR10 and CIFAR100 · CIFAR10 and CIFAR100 | Saddle loss | Helped |
| Use CIFAR100 rather than CIFAR10 | ResNets and DenseNets · CIFAR100 versus CIFAR10 | Saddle loss | Hurt |
Closest papers by meaning
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (ICML 2024 · similarity 0.87)
- Flat Channels to Infinity in Neural Loss Landscapes (NeurIPS 2025 · similarity 0.86)
- Understanding Mode Connectivity via Parameter Space Symmetry (ICML 2025 · similarity 0.86)
- Simplicity Bias via Global Convergence of Sharpness Minimization (ICML 2024 · similarity 0.85)
- Exploring Landscapes for Better Minima along Valleys (NeurIPS 2025 · similarity 0.85)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 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.