论文标题
使用双向色散的灵活风险设计
Flexible risk design using bi-directional dispersion
论文作者
论文摘要
已经提出和研究了许多“风险”（例如CVAR，倾斜风险，DRO风险）的新颖概念，但是这些风险至少与上升空间上的损失尾巴的卑鄙一样敏感，并且倾向于忽略偏差。我们研究了一个补充的新风险类别，该类别以双向方式惩罚损失偏差，同时在尾巴敏感性方面具有比均值方差更大的灵活性。该课程使我们能够在没有明确梯度剪辑的情况下获得高概率的学习保证，而使用模拟和真实数据的经验测试则说明了对基于梯度的学习者产生的测试损失分布的关键特性的高度控制。
Many novel notions of "risk" (e.g., CVaR, tilted risk, DRO risk) have been proposed and studied, but these risks are all at least as sensitive as the mean to loss tails on the upside, and tend to ignore deviations on the downside. We study a complementary new risk class that penalizes loss deviations in a bi-directional manner, while having more flexibility in terms of tail sensitivity than is offered by mean-variance. This class lets us derive high-probability learning guarantees without explicit gradient clipping, and empirical tests using both simulated and real data illustrate a high degree of control over key properties of the test loss distribution incurred by gradient-based learners.
