Research map / Learning theory and algorithms / Sample complexity
Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses
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 wavelet-thresholding rather than a linear density estimator | Besov density estimation under Besov IPM losses · Besov density classes | Besov IPM risk | Helped |
| Use a sufficiently large ReLU GAN with wavelet-thresholding regularization | Besov density estimation · Smooth Besov density and discriminator classes | Besov IPM risk | Helped |
| Use linear estimators instead of estimators that adapt to inhomogeneous smoothness | Besov density estimation under Besov IPM losses · Besov density classes where linear estimators are sub-optimal | Besov IPM risk | Hurt |
| Use a weaker Besov IPM loss rather than a traditional L^p loss | Nonparametric distribution estimation · Besov distribution classes | Convergence rate | Helped |
Closest papers by meaning
- Nonparametric Density Estimation under Adversarial Losses (NeurIPS 2018 · similarity 0.93)
- Robust Density Estimation under Besov IPM Losses (NeurIPS 2020 · similarity 0.93)
- Sobolev GAN (ICLR 2018 · similarity 0.89)
- Non-asymptotic Error Bounds for Bidirectional GANs (NeurIPS 2021 · similarity 0.88)
- Non-Parametric Priors For Generative Adversarial Networks (ICML 2019 · similarity 0.87)
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution (ICML 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.