Research map / Learning theory and algorithms / Matrix and tensor methods
Ada-LISTA: Learned Solvers Adaptive to Varying Models
Aviad Aberdam, Alona Golts, Michael Elad
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 |
|---|---|---|---|
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 Barbara inpainting, 50% missing | PSNR (dB): 24.93 -> 26.09 | Improved |
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 Boat inpainting, 50% missing | PSNR (dB): 28.18 -> 30.03 | Improved |
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 House inpainting, 50% missing | PSNR (dB): 30.53 -> 32.36 | Improved |
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 Lena inpainting, 50% missing | PSNR (dB): 31.02 -> 32.50 | Improved |
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 Peppers inpainting, 50% missing | PSNR (dB): 26.75 -> 28.81 | Improved |
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 Hill inpainting, 50% missing | PSNR (dB): 29.64 -> 30.86 | Improved |
| replace FISTA with learned mask-adaptive Ada-LFISTA | FISTA · Set11 Man inpainting, 50% missing | PSNR (dB): 29.03 -> 30.67 | Improved |
| replace ISTA with Ada-LFISTA | ISTA · Set11 Barbara inpainting, 50% missing | PSNR (dB): 23.49 -> 26.09 | Improved |
Closest papers by meaning
- AdaFisher: Adaptive Second Order Optimization via Fisher Information (ICLR 2025 · similarity 0.84)
- AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation (NeurIPS 2026 · similarity 0.83)
- Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad (NeurIPS 2024 · similarity 0.83)
- Prodigy: An Expeditiously Adaptive Parameter-Free Learner (ICML 2024 · similarity 0.83)
- Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration (CVPR 2024 · similarity 0.83)
- Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization (ICML 2024 · similarity 0.83)
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.
