Research map / Optimization / Implicit bias and generalization
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Rohith Kuditipudi, Xiang Wang, Holden Lee, Yi Zhang, Zhiyuan Li, Wei Hu, Rong Ge, Sanjeev Arora
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 |
|---|---|---|---|
| Apply channel-wise dropout during training | VGG-11 · CIFAR-10 training | accuracy: 99% -> 95% | Hurt |
| Apply channel-wise dropout during training | VGG-11 · CIFAR-10 test | accuracy: 92% -> 91% | Hurt |
| Use the constructed path rather than direct parameter interpolation | Two noise-stable VGG-11 networks · CIFAR-10 | loss: 2.34 -> fairly low | Improved |
| Use the constructed path rather than direct parameter interpolation | Two noise-stable VGG-11 networks · CIFAR-10 | accuracy: 10% -> fairly high | Improved |
Closest papers by meaning
- Input Space Mode Connectivity in Deep Neural Networks (ICLR 2025 · similarity 0.85)
- Generalized Linear Mode Connectivity for Transformers (NeurIPS 2025 · similarity 0.82)
- Understanding Mode Connectivity via Parameter Space Symmetry (ICML 2025 · similarity 0.82)
- Optimizer-Induced Mode Connectivity: From AdamW to Muon (NeurIPS 2026 · similarity 0.81)
- Layer-wise linear mode connectivity (ICLR 2024 · similarity 0.79)
- On Linear Mode Connectivity of Mixture-of-Experts Architectures (NeurIPS 2025 · similarity 0.79)
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.
