AI Paper Atlas

Research map / Optimization / Optimizers

Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training

Risheng Liu, Xuan Liu, Shangzhi Zeng, Jin Zhang, Yixuan Zhang

ICML 2022 · Optimization › Optimizers · approach: Differentiating through inner loops · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
Jointly optimize training and hyper-training variables with BMOSparse coding · Set14PSNR: 15.59±0.81 -> 18.82±1.59; 15.64±0.87 -> 18.98±2.53Improved
Jointly optimize training and hyper-training variables with BMOSparse coding · Set14SSIM: 0.52±0.13 -> 0.63±0.16; 0.52±0.13 -> 0.65±0.15Improved
Compose the numerical PG operator with DRUNet in BMOImage deconvolution · Set3c, six image/noise settingsPSNR (dB): Butterfly, σ=1%: 34.18 -> 33.67; Leaves, σ=1%: 35.12 -> 35.39; Starfish, σ=1%: 33.91 -> 33.98; Butterfly, σ=3%: 29.45 ->Mixed
Use BMO with the RCDNet iterative architectureRain streak removal · Rain100LPSNR: 40.00 -> 40.07Improved
Use BMO with the RCDNet iterative architectureRain streak removal · Rain100HPSNR: 31.28 -> 30.96Hurt
Use BMO with the RCDNet iterative architectureRain streak removal · Rain100HSSIM: 0.903 -> 0.905Improved
Enforce a non-expansive learned mapping (ablation)BMO sparse coding · Sparse codinggradient of upper loss φ: nullImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy