Research map / Learning theory and algorithms / Prediction and decision losses
A Distribution Optimization Framework for Confidence Bounds of Risk Measures
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 the local Lipschitz constant (supremum distance) instead of the global constant for the CVaR confidence bound | Distribution optimization framework · CVaR, supremum distance | confidence bound tightness: (b-a)/alpha -> (b-F^{-1}((1-alpha-c)^+))/alpha | Helped |
| Use the exact optimization-based bound instead of the LLC-based bound for CVaR under a uniform distribution | Distribution optimization framework · CVaR, uniform distribution, supremum distance | confidence bound tightness | Helped |
| Use local instead of global Lipschitz constant for CVaR with Wasserstein distance (p=1) | Distribution optimization framework · CVaR, Wasserstein distance | Lipschitz constant | No clear effect |
Closest papers by meaning
- Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions (ICML 2020 · similarity 0.90)
- Concentration of risk measures: A Wasserstein distance approach (NeurIPS 2019 · similarity 0.90)
- A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits (AAAI 2022 · similarity 0.89)
- Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards (NeurIPS 2025 · similarity 0.88)
- Large-Scale Methods for Distributionally Robust Optimization (NeurIPS 2020 · similarity 0.88)
- Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.86)
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.