Research map / Optimization / Nonconvex and smooth optimization
Inertial Block Proximal Methods for Non-Convex Non-Smooth Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use repeated block updates (T_k>2) instead of cyclic updates (T_k=2) (ablation) | IBPG for NMF · Low-rank synthetic NMF | mean E(k): $1.672 \, 10^{-3} \pm 7.313 \, 10^{-4}$ -> $\mathbf{1.081 \, 10^{-3}} \pm 6.012 \, 10^{-4}$ | Helped |
| Use repeated block updates (T_k>2) instead of cyclic updates (T_k=2) (ablation) | IBPG for NMF · Urban and San Diego hyperspectral NMF | mean E(k) | Helped |
| Use two different extrapolation points for gradient evaluation and inertial force | IBPG · NMF | convergence speed | Helped |
| Use APGC's single extrapolation-point parameterization instead of the proposed IBPG configuration | IBPG · Low-rank synthetic NMF | mean E(k): $1.672 \, 10^{-3} \pm 7.313 \, 10^{-4}$ -> $1.729 \, 10^{-3} \pm 7.452 \, 10^{-4}$ | Hurt |
Closest papers by meaning
- Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares (ICML 2024 · similarity 0.88)
- Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks (NeurIPS 2024 · similarity 0.88)
- Non-convex Stochastic Composite Optimization with Polyak Momentum (ICML 2024 · similarity 0.88)
- Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization (ICLR 2024 · similarity 0.87)
- Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions (ICML 2024 · similarity 0.87)
- On the Crucial Role of Initialization for Matrix Factorization (ICLR 2025 · similarity 0.87)
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.