Research map / Probabilistic and scientific modeling / Variational and generative sampling
Goodness-of-Fit Testing for Discrete Distributions via Stein Discrepancy
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 KDSD goodness-of-fit test (difference Stein operator, exponentiated Hamming kernel) instead of MMD two-sample test | Ising model (10x10 lattice, d=100), T0=5 and T0=20 · Ising model goodness-of-fit testing | false-negative rate (Type-II error) | Helped |
| Use KDSD goodness-of-fit test instead of MMD two-sample test | Bernoulli RBM (M=50 visible, K=25 hidden) · Bernoulli RBM goodness-of-fit testing | false-negative rate (Type-II error) | Helped |
| Use KDSD goodness-of-fit test instead of MMD two-sample test | ERGM (20 nodes, d=190) · ERGM goodness-of-fit testing | false-negative rate (Type-II error) | Mixed |
| Use KDSD goodness-of-fit test instead of MMD two-sample test | All three models (Ising, RBM, ERGM) · false-positive rate at alpha=0.05 | false-positive rate (Type-I error) | No clear effect |
| Use the exponentiated Hamming kernel rather than the naive delta kernel for discrete inputs | KDSD on discrete spaces · discrete kernel choice | qualitative (curse of dimensionality) | No clear effect |
Closest papers by meaning
- A Kernelized Stein Discrepancy for Goodness-of-fit Tests (ICML 2016 · similarity 0.96)
- A Kernel Stein Test of Goodness of Fit for Sequential Models (ICML 2023 · similarity 0.94)
- A Kernel Test of Goodness of Fit (ICML 2016 · similarity 0.93)
- Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy (ICML 2023 · similarity 0.90)
- The Polynomial Stein Discrepancy for Assessing Moment Convergence (ICML 2025 · similarity 0.87)
- Kernel Quantile Embeddings and Associated Probability Metrics (ICML 2025 · similarity 0.84)
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.