Research map / Learning theory and algorithms / Prediction and decision losses
Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes
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 scalable rather than prior-work NDPP decomposition | NDPP learning · Amazon Baby Registries: Apparel | test log-likelihood: -9.64 -> -9.63 | No clear effect |
| Use scalable rather than prior-work NDPP decomposition | NDPP learning · Amazon Baby Registries: 3-category | AUC: 0.82 -> 0.82 | No clear effect |
| Use scalable rather than prior-work NDPP decomposition | NDPP learning · UK Retail | AUC: 0.66 -> 0.73 | Helped |
| Use scalable rather than prior-work NDPP decomposition | NDPP learning · UK Retail | MPR: 74.17 -> 76.79 | Helped |
| Use scalable rather than symmetric DPP | DPP learning · Instacart | AUC: 0.83 -> 0.85 | Helped |
| Use scalable rather than symmetric DPP | DPP learning · Million Song | AUC: 0.69 -> 0.77 | Helped |
| Use scalable rather than symmetric DPP | DPP learning · Million Song | test log-likelihood: -335.25 -> -317.16 | Helped |
| Use the new decomposition rather than prior-work NDPP decomposition | NDPP learning · Amazon Baby Registries: 3-category | training convergence speed: 1.07 \times faster | Helped |
| Use the new decomposition rather than prior-work NDPP decomposition | NDPP learning · UK Retail | training convergence speed: 8.31 \times faster | Helped |
| Use exact greedy rather than greedy local search | NDPP MAP inference · Amazon Baby Registries: Apparel | relative log-determinant error: 0.0336 $\pm$ 0.0066 | Mixed |
| Use exact greedy rather than stochastic greedy | NDPP MAP inference · Amazon Baby Registries: Apparel | relative log-determinant error: 0.1606 $\pm$ 0.0133 -> 0.0336 $\pm$ 0.0066 | Helped |
| Use exact greedy rather than MCMC sampling | NDPP MAP inference · Million Song | relative log-determinant error: 1.0493 $\pm$ 0.0607 -> 0.0052 $\pm$ 0.0017 | Helped |
Closest papers by meaning
- Scalable Sampling for Nonsymmetric Determinantal Point Processes (ICLR 2022 · similarity 0.94)
- Learning Nonsymmetric Determinantal Point Processes (NeurIPS 2019 · similarity 0.93)
- Kronecker Determinantal Point Processes (NeurIPS 2016 · similarity 0.92)
- Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes (ICML 2022 · similarity 0.91)
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives (NeurIPS 2026 · similarity 0.90)
- Small coresets via negative dependence: DPPs, linear statistics, and concentration (NeurIPS 2024 · similarity 0.87)
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.