Research map / Optimization / Nonconvex and smooth optimization
Riemannian adaptive stochastic gradient algorithms on matrix manifolds
Hiroyuki Kasai, Pratik Jawanpuria, Bamdev Mishra
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Adapt row and column subspaces using covariance-based weights | RASA-LR · PCA synthetic, MNIST, and COIL100 | optimality gap | Improved |
| Adapt row and column subspaces using covariance-based weights | RASA-LR · ICA YaleB and COIL100 | relative optimality gap | Improved |
| Adapt row and column subspaces using covariance-based weights | RASA-LR · MovieLens-10M and MovieLens-1M | test generalization performance | Improved |
| Adapt row and column subspaces using covariance-based weights | RASA-LR · MovieLens-10M and MovieLens-1M | training convergence speed | Improved |
| Replace row-and-column subspace adaptation with per-entry vectorized adaptation (ablation) | RASA-LR · PCA, ICA, and matrix completion problems | performance | No clear effect |
| Adapt only the row subspace instead of both row and column subspaces (ablation) | RASA-LR · PCA, ICA, and matrix completion | performance | Mixed |
| Adapt only the column subspace instead of both row and column subspaces (ablation) | RASA-LR · PCA, ICA, and matrix completion | performance | Mixed |
Closest papers by meaning
- Riemannian Adaptive Optimization Methods (ICLR 2019 · similarity 0.92)
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.91)
- Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold (JMLR 2022 · similarity 0.90)
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.90)
- Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method (ICML 2025 · similarity 0.89)
- Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds (NeurIPS 2025 · 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.
