Research map / Learning theory and algorithms / Kernels and regression theory
Learning the optimal Tikhonov regularizer for inverse problems
Giovanni S Alberti, Ernesto De Vito, Matti Lassas, Luca Ratti, Matteo Santacesaria
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 |
|---|---|---|---|
| increase training sample size m from 3e3 to 3e5 | supervised and unsupervised learned Tikhonov regularizers · synthetic 1D denoising | excess risk | Improved |
| use unsupervised learning instead of supervised learning of the regularizer | learned Tikhonov regularizer · synthetic 1D denoising | excess risk | Improved |
| increase discretization size N | learned Tikhonov regularizer · synthetic 1D denoising | excess risk decay rate | No clear effect |
Closest papers by meaning
- Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation (ICML 2024 · similarity 0.88)
- DEALing with Image Reconstruction: Deep Attentive Least Squares (ICML 2025 · similarity 0.86)
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization (NeurIPS 2025 · similarity 0.86)
- NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems (NeurIPS 2025 · similarity 0.86)
- Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems (NeurIPS 2024 · similarity 0.86)
- Why Learning Rediscovers the Closed-Form Diagonal Regularizer (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.
