Research map / Optimization / Implicit bias and generalization
Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation
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 |
|---|---|---|---|
| optimize the un-trained deep decoder until convergence instead of using optimal early stopping | 5-layer deep decoder · fastMRI, 8-fold undersampled k-space | MSE | Hurt |
| use early stopping at about 2000 iterations rather than optimizing until convergence | 5-layer deep decoder · fastMRI, 8-fold undersampled k-space | MSE | Helped |
| use the smoother blue image rather than the non-smooth grass texture | deep decoder with gradient descent · compressive sensing, m = n/4 | measurement loss | Helped |
Closest papers by meaning
- Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior (CVPR 2019 · similarity 0.90)
- Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors (NeurIPS 2019 · similarity 0.90)
- Training Image Estimators without Image Ground Truth (NeurIPS 2019 · similarity 0.90)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.89)
- Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing (CVPR 2025 · similarity 0.87)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.86)
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.