Research map / Learning theory and algorithms / Sample complexity
Testing Determinantal Point Processes
Khashayar Gatmiry, Maryam Aliakbarpour, Stefanie Jegelka
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 |
|---|---|---|---|
| assume (alpha, zeta)-normal DPPs with known alpha and zeta | DPP tester · DPP testing, theory | log factor in sample complexity | Improved |
| epsilon or alpha not too small | DPP tester · (alpha, zeta)-normal DPPs | log factor in sample complexity | Improved |
| use moment-based learner instead of the section learner (single robust test) | DPP tester · DPP testing, theory | running time vs sample complexity | Mixed |
| assume constant cycle sparsity | DPP tester · DPP testing lower bound | sample complexity | No clear effect |
Closest papers by meaning
- Learning Determinantal Point Processes with Moments and Cycles (ICML 2017 · similarity 0.89)
- Sampling from a k-DPP without looking at all items (NeurIPS 2020 · similarity 0.88)
- Faster Greedy MAP Inference for Determinantal Point Processes (ICML 2017 · similarity 0.87)
- Kronecker Determinantal Point Processes (NeurIPS 2016 · similarity 0.87)
- Small coresets via negative dependence: DPPs, linear statistics, and concentration (NeurIPS 2024 · similarity 0.86)
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives (NeurIPS 2026 · similarity 0.85)
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.
