Research map / Optimization / Nonconvex and smooth optimization
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent
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 randomized rounding after OPGD in doubly stochastic matrices | GMSSC online learning · GMSSC | regret upper bound: 28 | Helped |
| Specialize randomized rounding to the K(R)=1 case | GMSSC online learning · MSSC | regret upper bound: 28 -> 11.713 | Helped |
| Use deterministic rounding instead of randomized rounding | OPGD online learning · MSSC | regret upper bound: 2 \cdot \max_{t}|R_t|; lower bound: \frac{\max_{t}|R_t|}{2} | Mixed |
| Represent rankings with doubly stochastic matrices and optimize with OPGD | GMSSC online learning · GMSSC relaxation | average fractional access cost regret: O\left (\frac{n^{5.5}}{\epsilon \sqrt{T}}\right) | Helped |
Closest papers by meaning
- Online Learning to Rank with Features (ICML 2019 · similarity 0.86)
- Selective Preference Aggregation (ICML 2025 · similarity 0.86)
- Just Sort It! A Simple and Effective Approach to Active Preference Learning (ICML 2017 · similarity 0.85)
- TopRank: A practical algorithm for online stochastic ranking (NeurIPS 2018 · similarity 0.84)
- Adaptively Learning to Select-Rank in Online Platforms (ICML 2024 · similarity 0.84)
- Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective (ICML 2025 · similarity 0.83)
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.