Research map / Learning theory and algorithms / Prediction and decision losses
Learning to Optimize on SPD Manifolds
Zhi Gao, Yuwei Wu, Yunde Jia, Mehrtash Harandi
Check 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 |
|---|---|---|---|
| Use the learned SPD optimizer rather than the strongest reported hand-designed optimizer | SPD optimization · Kylberg | classification accuracy: 84.37 vs 83.19 | Improved |
| Use the learned SPD optimizer rather than the strongest reported hand-designed optimizer | SPD optimization · CUB | classification accuracy: 70.97 vs 70.44 | Improved |
| Replace conventional LSTM with the symmetric-structure-preserving mLSTM (ablation) | Learned SPD optimizer · Kylberg clustering | log loss: 2.47 and 1.39 without mLSTM; 0.16 and -0.77 for ours | Improved |
| Add experience replay and an experience pool (ablation) | Learned SPD optimizer · Kylberg clustering | convergence rate | Improved |
| Add a skip-connection to fit the residual search direction (ablation) | Learned SPD optimizer · Kylberg clustering | convergence | Improved |
| Use the learned SPD optimizer instead of RSGD | SPD optimization · MNIST | optimization time: 76.757 vs 74.980 | Hurt |
| Use the learned SPD optimizer instead of RSGD | SPD optimization · Kylberg | optimization time: 378.996 vs 367.995 | Hurt |
| Use the learned SPD optimizer instead of RSGD | SPD optimization · CUB | optimization time: 154.370 vs 150.262 | Hurt |
Closest papers by meaning
- Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds (ICML 2024 · similarity 0.88)
- Riemannian Geometric-based Meta Learning (AAAI 2025 · similarity 0.88)
- Implicit Riemannian Optimism with Applications to Min-Max Problems (ICML 2025 · similarity 0.86)
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.86)
- Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method (ICML 2025 · similarity 0.86)
- Robust Hyperbolic Learning with Curvature-Aware Optimization (NeurIPS 2025 · 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.
