Research map / Optimization / Nonconvex and smooth optimization
Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
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 |
|---|---|---|---|
| Use Proximal-SGD instead of plain SGD | Shallow networks trained with 1-path-norm regularization · MNIST, Fashion-MNIST, and Kuzushiji-MNIST | regularized cross-entropy loss | Helped |
| Use 1-path-norm regularization instead of ℓ1 regularization | Shallow neural networks · MNIST, Fashion-MNIST, and Kuzushiji-MNIST | robust test error as a function of sparsity | Mixed |
| Use 1-path-norm regularization instead of ℓ1 regularization | Shallow neural networks · Adversarial test examples | robust test error | Helped |
| Use layer-wise constraints or 1-path-norm regularization instead of ℓ1 regularization | Shallow neural networks · Adversarial test examples | robust test error | Helped |
| Use 1-path-norm regularization instead of layer-wise constraints | Shallow neural networks · Adversarial test examples | robust test error | Helped |
Closest papers by meaning
- Adaptive Proximal Gradient Methods for Structured Neural Networks (NeurIPS 2021 · similarity 0.88)
- A path-norm toolkit for modern networks: consequences, promises and challenges (ICLR 2024 · similarity 0.87)
- The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks (ICLR 2023 · similarity 0.86)
- Approximation theory for 1-Lipschitz ResNets (NeurIPS 2025 · similarity 0.86)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · similarity 0.85)
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks (ICLR 2024 · 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.