Research map / Learning theory and algorithms / Sample complexity
Concentration Inequalities for Conditional Value at Risk
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 DKW-based CVaR lower bound instead of Brown's lower bound | CVaR lower confidence bound · Synthetic log-normal and beta distributions | bound tightness | Helped |
| use the DKW-based CVaR upper bound instead of Brown's upper bound | CVaR upper confidence bound · Synthetic distributions, n=10,000, alpha=0.05, delta=0.05 | bound tightness | Helped |
| vary the confidence level delta from 0 to 0.5 | Both new bounds vs Brown · Synthetic distributions | bound tightness | Helped |
| vary the percentile alpha, small alpha for upper bound | New upper bound vs Brown's · Beta distribution with frequent samples near lower bound | upper bound tightness | Mixed |
| vary the sample size n | New bounds vs Brown · Synthetic distributions | bound tightness | Helped |
| remove the need for known upper bound on the variable | New lower bound · Heavy-tailed log-normal | applicability and tightness | Helped |
Closest papers by meaning
- Concentration of risk measures: A Wasserstein distance approach (NeurIPS 2019 · similarity 0.92)
- Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions (ICML 2020 · similarity 0.90)
- PAC-Bayesian Bound for the Conditional Value at Risk (NeurIPS 2020 · similarity 0.89)
- A Distribution Optimization Framework for Confidence Bounds of Risk Measures (ICML 2023 · similarity 0.87)
- Concentration Inequalities for General Functions of Heavy-Tailed Random Variables (ICML 2024 · similarity 0.85)
- Risk Estimation in a Markov Cost Process: Lower and Upper Bounds (ICML 2024 · 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.