Research map / Learning theory and algorithms / Matrix and tensor methods
Efficient Non-Oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee
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 NOR instead of RPDR or DSRR | ERM with randomized dimensionality reduction · Synthetic datasets | testing performance | Helped |
| Use NOR with exponential-decay data | Synthetic datasets · exp-1 | testing performance | No clear effect |
| Use NOR as singular-value decay becomes slower | Synthetic datasets · poly-0.5 and poly-1 | testing performance | Hurt |
| Use RS rather than RH or RG | NOR · Synthetic datasets with fast singular-value decay | testing performance | No clear effect |
| Use RS rather than RH or RG | NOR · Synthetic datasets with slower singular-value decay | testing performance | Hurt |
| Use NOR instead of RPDR, DSRR, or RP | Binary classification · RCV1.b and Splice | testing error | Helped |
| Use NOR instead of RPDR, DSRR, or RP | Binary classification · RCV1.b and Splice | auPRC | Helped |
| Use RS rather than RH or RG | Oblivious randomized reduction approaches · RCV1.b and Splice | testing performance | Hurt |
| Use RS rather than RH or RG | NOR · RCV1.b and Splice | testing performance | No clear effect |
| Use NOR instead of RP | Multi-class classification · RCV1.m and News20 | testing performance | Helped |
| Use NOR instead of RP | Multi-class classification · RCV1.m and News20 | running time | Helped |
| Use RH or RS rather than RG | Randomized reduction approaches · RCV1.m and News20 | running time | Helped |
Closest papers by meaning
- Differentially Private High-dimensional Variable Selection via Integer Programming (NeurIPS 2025 · similarity 0.86)
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.85)
- Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures (ICML 2025 · similarity 0.84)
- Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence (ICML 2025 · similarity 0.84)
- Dimension-free deterministic equivalents and scaling laws for random feature regression (NeurIPS 2024 · similarity 0.84)
- Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming (NeurIPS 2024 · 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.