Research map / Optimization / Optimizers
Cogradient Descent for Bilinear Optimization
Check 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 |
|---|---|---|---|
| Apply CoGD rather than FFCSC to convolutional sparse coding | CSC · Image reconstruction, fruit and city datasets | PSNR (dB): +1.01 db | Helped |
| Apply CoGD rather than FFCSC to convolutional sparse coding | CSC · Image reconstruction, fruit and city datasets | SSIM: +0.003 | Helped |
| Apply CoGD rather than FFCSC to convolutional sparse coding | CSC · Image inpainting, fruit and city datasets, 75% subsampling | PSNR (dB): +1.47 db | Helped |
| Apply CoGD rather than FFCSC to convolutional sparse coding | CSC · Image inpainting, fruit and city datasets, 75% subsampling | SSIM: +0.016 | Helped |
| Add CoGD pruning instead of using SGD (ablation) | ResNet-18 · CIFAR-10 | accuracy (%): 94.81 -> 95.30 | Helped |
| Add CoGD pruning instead of using SGD (ablation) | ResNet-18 · CIFAR-10 | FLOPs (M): 376.12 / 555.43 -> 274.74 / 555.43 | Helped |
| Add CoGD rather than train without CoGD (ablation) | ResNet-18 pruning · CIFAR-10 | error rate: 5.19% -> 4.70% | Helped |
| Add CoGD rather than train without CoGD (ablation) | ResNet-18 pruning · CIFAR-10 | FLOPs reduction: 0.32× -> 0.51× | Helped |
Closest papers by meaning
- Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization (ICLR 2024 · similarity 0.84)
- Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares (ICML 2024 · similarity 0.83)
- Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization (NeurIPS 2024 · similarity 0.83)
- LPGD: A General Framework for Backpropagation through Embedded Optimization Layers (ICML 2024 · similarity 0.83)
- Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free Algorithm (ICLR 2024 · similarity 0.83)
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization (NeurIPS 2025 · similarity 0.82)
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.