Research map / Optimization / Implicit bias and generalization
Lifted Proximal Operator Machines
Jia Li, Cong Fang, Zhouchen Lin
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 LPOM instead of SGD | Fully connected feed-forward network · MNIST | test accuracy: 98.0% -> 98.2% | Improved |
| Use LPOM instead of SGD | Fully connected feed-forward network · CIFAR-10 | test accuracy: 47.5% -> 52.5% | Improved |
| Use LPOM instead of the prior non-gradient method | Fully connected network · MNIST, five reported architectures | accuracy: 89.8% -> 97.7%; 87.5% -> 96.9%; 86.5% -> 97.1%; 85.3% -> 96.2%; 77.0% -> 96.1% | Improved |
| Use LPOM instead of SGD or the prior non-gradient method | Fully connected network · SVHN | test accuracy: 95.0% -> 98.3%; 96.5% -> 98.3% | Improved |
Closest papers by meaning
- Training Neural Networks by Lifted Proximal Operator Machines (TPAMI 2020 · similarity 0.97)
- What's in a Prior? Learned Proximal Networks for Inverse Problems (ICLR 2024 · similarity 0.87)
- MgNO: Efficient Parameterization of Linear Operators via Multigrid (ICLR 2024 · similarity 0.86)
- A Bregman Proximal Viewpoint on Neural Operators (ICML 2025 · similarity 0.86)
- LPGD: A General Framework for Backpropagation through Embedded Optimization Layers (ICML 2024 · similarity 0.85)
- Optimization for Neural Operators can Benefit from Width (ICML 2025 · similarity 0.84)
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.
