Research map / Optimization / Nonconvex and smooth optimization
A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning
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 |
|---|---|---|---|
| geometrically diminishing step size instead of constant, O(1/k) or O(1/sqrt k) step size (ablation) | projected Riemannian subgradient method · DPCP synthetic (D=100, c=10, 70% outliers) | convergence rate | Helped |
| geometrically diminishing step size instead of O(1/k^(3/8)) step size (ablation) | projected Riemannian subgradient method · orthogonal dictionary learning (D=70, rho=0.3) | convergence rate | Helped |
| decay factor beta of 0.5 or 0.6 versus 0.7 and above (ablation) | geometric step size mu_k=0.01*beta^k · DPCP synthetic | convergence | Mixed |
Closest papers by meaning
- Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach (ICML 2021 · similarity 0.91)
- Efficient Dictionary Learning with Gradient Descent (ICML 2019 · similarity 0.88)
- Local Linear Convergence of Gradient Methods for Subspace Optimization via Strict Complementarity (NeurIPS 2022 · similarity 0.87)
- Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension (ICLR 2022 · similarity 0.87)
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing (NeurIPS 2025 · similarity 0.85)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.85)
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.