Research map / Learning theory and algorithms / Matrix and tensor methods
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing
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 global l2-RIP sensing operator with Conditionally Independent RIP (fresh mini-batch of instances each iteration) in One-Pass gFM | gFM / symmetric rank-one matrix sensing · Gaussian features, noise-free, rank-k M* | recovery error decay / sample complexity | Helped |
| Use one-pass streaming mini-batches (fresh instances per update) with matrix-vector products only | One-Pass gFM · Gaussian features, streaming | memory complexity | Helped |
| Apply soft-deflation to remove the (sigma_1/sigma_k)^2 factor from sample complexity when M* is ill-conditioned | One-Pass gFM · ill-conditioned M* | sampling complexity | No clear effect |
| Include first-order term w* in the model (gFM) versus folding it into an extended rank-(k+1) matrix sensing problem | gFM · Gaussian features, theory | applicability of rank-one sensing guarantees | Hurt |
Closest papers by meaning
- RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees (NeurIPS 2025 · similarity 0.87)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · similarity 0.87)
- Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning (ICML 2025 · similarity 0.86)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.86)
- In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting (AAAI 2025 · similarity 0.86)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (ICLR 2024 · similarity 0.86)
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.