Research map / Optimization / Nonconvex and smooth optimization
Explicitly Imposing Constraints in Deep Networks via Conditional Gradients Gives Improved Generalization and Faster Convergence
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 |
|---|---|---|---|
| train ResNet-32 with Frobenius-norm constrained Conditional Gradient instead of SGD | ResNet-32 · CIFAR10 | test error: 8% -> 6% | Helped |
| increase Frobenius-norm constraint lambda (ablation) | CG on ResNet-32 · CIFAR10 | training error, loss, test error | Helped |
| use Path-CG instead of Path-SGD for path-norm constrained training | 2-layer fully connected network · MNIST/CIFAR/SVHN | accuracy | No clear effect |
| use Path-CG instead of Path-SGD for path-norm constrained training | 2-layer fully connected network · path norm stability | path norm | Helped |
| train DC-GAN discriminator with Frobenius-constrained CG instead of SGD | DC-GAN · image inpainting (CelebA/LFW) | MSE/SSIM/FID | Helped |
Closest papers by meaning
- Better Training using Weight-Constrained Stochastic Dynamics (ICML 2021 · similarity 0.88)
- Understanding Generalization and Optimization Performance of Deep CNNs (ICML 2018 · similarity 0.88)
- A General Regret Bound of Preconditioned Gradient Method for DNN Training (CVPR 2023 · similarity 0.88)
- Improving Deep Learning Optimization through Constrained Parameter Regularization (NeurIPS 2024 · similarity 0.88)
- Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks (ICLR 2018 · similarity 0.88)
- Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization (NeurIPS 2024 · similarity 0.87)
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.