arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.00505math.OC
收藏

基于超分位数的学习:使用基于梯度的optimization的直接方法

Superquantile-based learning: a direct approach using gradient-based optimization

Yassine Laguel, Jérôme Malick, Zaid Harchaoui

摘要:

我们考虑一种监督学习的形式,它赋予模型从训练到测试的分布变化的鲁棒性。该公式取决于超分位数风险度量,也称为条件风险值,它在最近的机器学习和信号处理应用中表现出了希望。我们表明,由于直接平滑的超分位数函数,基于超分位数的学习目标是服从基于梯度的优化,使用批量优化算法,如梯度下降或拟牛顿算法,或使用随机最优化算法,如随机梯度算法。配套软件SPQR在Python中实现了所描述的算法,并允许从业者尝试基于超分位数的监督学习。

英文摘要:

We consider a formulation of supervised learning that endows models with robustness to distributional shifts from training to testing. The formulation hinges upon the superquantile risk measure, also known as the conditional value-at-risk, which has shown promise in recent applications of machine learning and signal processing. We show that, thanks to a direct smoothing of the superquantile function, a superquantile-based learning objective is amenable to gradient-based optimization, using batch optimization algorithms such as gradient descent or quasi-Newton algorithms, or using stochastic optimization algorithms such as stochastic gradient algorithms. A companion software SPQR implements in Python the algorithms described and allows practitioners to experiment with superquantile-based supervised learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑