AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Task Embedded Coordinate Update: A Realizable Framework for Multivariate Non-Convex Optimization

Yiyang Wang, Risheng Liu, Long Ma, Xiaoliang Song

AAAI 2019 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 4 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
Use ADMM for the dictionary D subproblem rather than PITH for the sparse-coding W subproblem (ablation)TECU for ℓ0DL · ℓ0DL synthetic, n=64computation time (s): 2.22s vs nearly 600sImproved
Embed ADMM for the D subproblemTECU for ℓ0DL · ℓ0DL syntheticcomputation time (s)Improved
Embed PITH for the W subproblem instead of using prox-linear updates (ablation)TECU for ℓ0DL · ℓ0DL syntheticcomputation time (s): 2.22s vs nearly 600sHurt
Embed a residual-type CNN for illumination-layer updatesTECU for low-light image enhancement · Low-light image enhancement examplePSNRImproved
Embed a residual-type CNN in the coordinate-descent scheme rather than use the classical CD scheme aloneTECU for low-light image enhancement · Low-light image enhancement examplePSNRImproved
Embed a residual-type CNN for illumination-layer updatesTECU for low-light image enhancement · NASANIQE: 3.43 -> 3.41Improved
Embed a residual-type CNN for illumination-layer updatesTECU for low-light image enhancement · Non-uniformNIQE: 2.94 -> 2.91Improved
Use TECU rather than the strongest listed baseline, BCUℓ0DL · ℓ0DL synthetic, n=64computation time (s): 3.87 -> 2.22Improved
Use TECU rather than the strongest listed baseline, BCUℓ0DL · ℓ0DL synthetic, n=144computation time (s): 14.45 -> 11.96Improved
Use TECU rather than the strongest listed baseline, BCUℓ0DL · ℓ0DL synthetic, n=256computation time (s): 100.19 -> 75.19Improved

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