Research map / Optimization / Nonconvex and smooth optimization
A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
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 |
|---|---|---|---|
| replace full gradient descent with variance-reduced semi-stochastic low-rank SGD (LRSVRG) | matrix completion collaborative filtering · Jester1/2/3 | RMSE and CPU time | Helped |
| replace full gradient descent with variance-reduced semi-stochastic low-rank SGD (LRSVRG) | matrix completion, simulated noiseless and noisy data · synthetic matrix completion | convergence vs effective data passes | Helped |
Closest papers by meaning
- Global Optimality of Local Search for Low Rank Matrix Recovery (NeurIPS 2016 · similarity 0.91)
- Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation (ICML 2016 · similarity 0.90)
- Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery (NeurIPS 2021 · similarity 0.90)
- Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent (NeurIPS 2016 · similarity 0.90)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · similarity 0.89)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.88)
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.