Research map / Learning theory and algorithms / Sample complexity
Learning Determinantal Point Processes with Moments and Cycles
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 |
|---|---|---|---|
| Increase the cycle sparsity of the kernel graph | Moments and cycles · DPP kernel estimation | sample complexity for sign recovery: n = O\Big( \big(\frac{C}{\alpha}\big)^{2\ell}+ \frac{\log N}{\alpha^2 \varepsilon^2} \Big) | Hurt |
| Use the moments-and-cycles estimator rather than an unspecified alternative | DPP kernel estimation · DPP kernel estimation | sample complexity | Helped |
| Recover the sparsity pattern before recovering signs | Moments and cycles on cycle-graph kernels · Random cycle-graph matrices | sign recovery success | Mixed |
| Use a shortest maximal cycle basis and moments for sign recovery | Moments and cycles on cycle- and clique-graph kernels · Random cycle- and clique-graph matrices | sign recovery conditional on graph recovery | Helped |
Closest papers by meaning
- Kronecker Determinantal Point Processes (NeurIPS 2016 · similarity 0.92)
- Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem (NeurIPS 2018 · similarity 0.92)
- Faster Greedy MAP Inference for Determinantal Point Processes (ICML 2017 · similarity 0.91)
- Nonparametric estimation of continuous DPPs with kernel methods (NeurIPS 2021 · similarity 0.90)
- 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 0.88)
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.