Research map / Adversarial robustness and security / Certified and empirical robustness
Learning Provably Robust Estimators for Inverse Problems via Jittering
Anselm Krainovic, Mahdi Soltanolkotabi, Reinhard Heckel
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 |
|---|---|---|---|
| Train the denoiser with Gaussian jittering instead of standard training | U-net · Gaussian image denoising | worst-case risk | Improved |
| Use jittering instead of adversarial training | U-net · Gaussian image denoising | worst-case risk | No clear effect |
| Train with Gaussian jittering instead of standard training | U-net · Image deconvolution | worst-case risk | Improved |
| Use jittering instead of adversarial training | U-net · Image deconvolution | worst-case risk | Hurt |
| Train with Gaussian jittering instead of standard training | U-net · Compressive sensing | worst-case risk | Improved |
| Use jittering instead of adversarial training | U-net · Compressive sensing | worst-case risk | Hurt |
| Add Gaussian jittering noise during training | Linear estimator · Subspace Gaussian denoising | worst-case risk | No clear effect |
| Increase the desired robustness level | Optimal robust denoiser · Subspace Gaussian denoising | standard risk | Hurt |
| Optimize the jittering noise level for the desired robustness | U-net · Gaussian image denoising | worst-case risk | Improved |
| Use jittering rather than adversarial training | U-net · Inverse problems | training computational cost | Improved |
| Use jittering for a general linear inverse problem with unequal singular values | Linear estimator · General linear inverse problems | worst-case risk | Hurt |
Closest papers by meaning
- Stochastic Solutions for Linear Inverse Problems using the Prior Implicit in a Denoiser (NeurIPS 2021 · similarity 0.89)
- SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures (ICML 2025 · similarity 0.89)
- Solving Inverse Problems With Deep Neural Networks – Robustness Included? (TPAMI 2022 · similarity 0.88)
- Stochastic Deep Restoration Priors for Imaging Inverse Problems (ICML 2025 · similarity 0.87)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.86)
- Exact Posterior Score Estimation for Solving Linear Inverse Problems (NeurIPS 2026 · 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.
