Research map / Probabilistic and scientific modeling / Variational and generative sampling
Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximation
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 Wasserstein optimistic likelihood instead of the exponential kernel approximation | Probabilistic classifier · Banknote Authentication | area under the precision-recall curve: 99.05 -> 100.00 | Helped |
| Use Wasserstein optimistic likelihood instead of the exponential kernel approximation | Probabilistic classifier · Climate Model | area under the precision-recall curve: 93.80 -> 93.40 | Hurt |
| Use Wasserstein optimistic likelihood instead of the exponential kernel approximation | Probabilistic classifier · Ionosphere | area under the precision-recall curve: 91.02 -> 98.79 | Helped |
| Use Moment optimistic likelihood instead of the exponential kernel approximation | Probabilistic classifier · Blood Transfusion | area under the precision-recall curve: 64.91 -> 71.28 | Helped |
| Use Moment optimistic likelihood instead of the exponential kernel approximation | Probabilistic classifier · Climate Model | area under the precision-recall curve: 93.80 -> 81.94 | Hurt |
| Use a Wasserstein ambiguity set rather than a moment ambiguity set | Optimistic likelihood classifier · Heart | area under the precision-recall curve: 86.87 -> 75.86 | Hurt |
| Use a Wasserstein ambiguity set rather than a moment ambiguity set | Optimistic likelihood classifier · Ionosphere | area under the precision-recall curve: 97.05 -> 98.79 | Helped |
| Use a Wasserstein ambiguity set rather than a moment ambiguity set | Optimistic likelihood classifier · Seismic Bumps | area under the precision-recall curve: 75.68 -> 65.89 | Hurt |
| Use the Wasserstein likelihood approximation instead of the exponential kernel approximation | Posterior inference on beta-binomial synthetic data · Beta-binomial inference | KL divergence to true discretized posterior | No clear effect |
| Increase the number of training samples | KL and Wasserstein optimistic likelihood approximations · Beta-binomial inference | optimal ambiguity-set radius | Helped |
Closest papers by meaning
- Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.88)
- An Iterative Min-Min Optimization Method for Sparse Bayesian Learning (ICML 2024 · similarity 0.85)
- Principled Preferential Bayesian Optimization (ICML 2024 · similarity 0.85)
- Direct Fisher Score Estimation for Likelihood Maximization (NeurIPS 2025 · similarity 0.85)
- Near-Optimality of Contrastive Divergence Algorithms (NeurIPS 2024 · similarity 0.85)
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.85)
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.