Adaptive Sampling for Stochastic Risk-Averse Learning
Adaptive Sampling for Stochastic Risk-Averse Learning
复制标题
DOI：
--
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Sebastian Curi;K. Levy;S. Jegelka;A. Krause
中科院分区：
文献类型：
--
作者：
Sebastian Curi;K. Levy;S. Jegelka;A. Krause
我们考虑以风险规避的方式训练机器学习模型的问题。特别地，我们提出一种自适应采样算法，用于随机优化损失分布的条件风险价值（CVaR）。我们使用CVaR的分布鲁棒公式将问题表述为两个参与者之间的零和博弈。我们的方法为每个参与者使用一种高效的无遗憾算法来解决该博弈。关键的是，由于其实现依赖于从行列式点过程中采样，我们可以将这些算法应用于大规模场景。最后，我们通过实验证明了它在大规模凸和非凸学习任务上的有效性。
We consider the problem of training machine learning models in a risk-averse manner. In particular, we propose an adaptive sampling algorithm for stochastically optimizing the Conditional Value-at-Risk (CVaR) of a loss distribution. We use a distributionally robust formulation of the CVaR to phrase the problem as a zero-sum game between two players. Our approach solves the game using an efficient no-regret algorithm for each player. Critically, we can apply these algorithms to large-scale settings because the implementation relies on sampling from Determinantal Point Processes. Finally, we empirically demonstrate its effectiveness on large-scale convex and non-convex learning tasks.