Research map / Learning theory and algorithms / Prediction and decision losses
Learning 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 |
|---|---|---|---|
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Amazon Apparel | MPR: 62.63 ± 1.81 -> 72.20 ± 3.07 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Amazon Apparel | AUC: 0.68 ± 0.05 -> 0.77 ± 0.03 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Amazon 3-category | MPR: 61.0 ± 2.73 -> 74.10 ± 2.49 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Amazon 3-category | AUC: 0.76 ± 0.03 -> 0.82 ± 0.02 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · UK Retail | MPR: 69.95 ± 1.32 -> 74.17 ± 1.37 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · UK Retail | AUC: 0.58 ± 0.01 -> 0.66 ± 0.01 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Synthetic low-sparsity data | AUC: approximately 0.8 for both models | No clear effect |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Synthetic high-sparsity data (14 disjoint groups) | AUC: 0.5 -> 0.7 | Helped |
| Replace the symmetric DPP with the nonsymmetric DPP | DPP · Synthetic popularity-based positives with disjoint groups | AUC: 0.7 -> 0.75 | Helped |
Closest papers by meaning
- Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes (ICLR 2021 · similarity 0.93)
- Scalable Sampling for Nonsymmetric Determinantal Point Processes (ICLR 2022 · similarity 0.92)
- Low-Rank Factorization of Determinantal Point Processes (AAAI 2017 · similarity 0.92)
- Kronecker Determinantal Point Processes (NeurIPS 2016 · similarity 0.90)
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives (NeurIPS 2026 · similarity 0.89)
- 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.