Research map / Optimization / Nonconvex and smooth optimization
Stochastic Non-Convex Ordinal Embedding With Stabilized Barzilai-Borwein Step Size
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 |
|---|---|---|---|
| Use SVRG-SBBε instead of fixed-step SVRG | Non-convex GNMDS ordinal embedding · Synthetic dataset | mean runtime (seconds): 2.8919 -> 0.4858 | Helped |
| Use SVRG-SBBε instead of fixed-step SVRG | Non-convex STE ordinal embedding · Synthetic dataset | mean runtime (seconds): 2.4068 -> 0.5773 | Helped |
| Use SVRG-SBBε instead of fixed-step SVRG | Non-convex TSTE ordinal embedding · Synthetic dataset | mean runtime (seconds): 1.9250 -> 0.4726 | Helped |
| Use SVRG-SBBε rather than SVRG for GNMDS | GNMDS image retrieval embedding · SUN397 5% noise | MAP: 0.3872 -> 0.3887 | Helped |
| Use SVRG-SBBε rather than SVRG for STE | STE image retrieval embedding · SUN397 10% noise | MAP: 0.3245 -> 0.3896 | Helped |
| Use SVRG-SBBε rather than SVRG for TSTE | TSTE image retrieval embedding · SUN397 10% noise | MAP: 0.2493 -> 0.3897 | Helped |
| Use positive ε stabilization rather than SBB₀ (ablation) | SVRG-SBB ordinal embedding · SUN397, GNMDS, 0% noise | MAP: 0.3941 -> 0.3363 | Hurt |
| Use positive ε stabilization rather than SBB₀ (ablation) | SVRG-SBB ordinal embedding · SUN397, GNMDS, 5% noise | MAP: 0.3700 -> 0.3887 | Helped |
| Use positive ε stabilization rather than SBB₀ (ablation) | SVRG-SBB ordinal embedding · SUN397, STE, 0% noise | MAP: 0.3968 -> 0.3940 | Hurt |
| Use positive ε stabilization rather than SBB₀ (ablation) | SVRG-SBB ordinal embedding · SUN397, TSTE, 5% noise | MAP: 0.3917 -> 0.3845 | Hurt |
| Use positive ε stabilization rather than SBB₀ (ablation) | SVRG-SBB ordinal embedding · Synthetic dataset | mean runtime (seconds): 0.4347 vs 0.4858; 0.6052 vs 0.5773; 0.7906 vs 0.4726 | Mixed |
Closest papers by meaning
- Finite Sample Prediction and Recovery Bounds for Ordinal Embedding (NeurIPS 2016 · similarity 0.88)
- Less but Better: Generalization Enhancement of Ordinal Embedding via Distributional Margin (AAAI 2019 · similarity 0.88)
- Scaling Up Ordinal Embedding: A Landmark Approach (ICML 2019 · similarity 0.88)
- Optimization Can Learn Johnson Lindenstrauss Embeddings (NeurIPS 2024 · similarity 0.85)
- Sparse Dimensionality Reduction Revisited (ICML 2024 · similarity 0.85)
- Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization (ICML 2025 · similarity 0.84)
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.