|
| 摘要: |
| 本文研究了分布漂移情形下极小极大遗憾优化(minimax regretoptimization,MRO)的泛化性分析问题.通过引入条件风险价值(conditional value atrisk,CVaR)这一度量提出了一种新的学习框架,并从一致收敛分析的角度建立了其泛化误差界,实现了超额风险的多项式衰减率,将期望风险相关的泛化分析扩展到风险规避情形. |
| 关键词: 极小极大遗憾优化(MRO) 条件风险价值(CVaR) 分布漂移 泛化误差 |
| DOI： |
| 分类号:O29 |
| 基金项目: |
|
| GENERALIZATION ANALYSIS FOR CVaR-BASED MINIMAX REGRET OPTIMIZATION |
|
TAO Yan-fang,DENG Hao
|
| Abstract: |
| This paper analyzes the generalization of minimax regret optimization (MRO) under distribution shift. A new learning framework is proposed by injecting the measure of conditional value at risk (CVaR) into MRO, and its generalization error bound is established through the lens of uniform convergence analysis. The CVaR-based MRO can achieve the polynomial decay rate on the excess risk, which extends the generalization analysis associated with the expected risk to the risk-averse case. |
| Key words: Minimax regret optimization (MRO) conditional value at risk (CVaR) distribution shift generalization error |
