论文标题
在逐渐分布变化下进行随机优化的预测校正算法
Predictor-corrector algorithms for stochastic optimization under gradual distribution shift
论文作者
论文摘要
随机变化的随机优化问题在机器学习实践中经常出现（例如逐渐的域移动，对象跟踪，战略分类）。尽管大多数问题在离散时间都解决了，但基本过程通常是连续的。我们通过开发预测器 - 校正算法来利用这种潜在的连续性，以进行随机变化的随机优化。我们为迭代术提供了误差界，无论是在纯粹和嘈杂的访问损失函数的相关衍生物中的查询的情况下提供的误差范围。此外，我们（在几个示例中从理论上和经验上）表明，我们的方法优于不利用基本连续过程的非prespentor校正方法。
Time-varying stochastic optimization problems frequently arise in machine learning practice (e.g. gradual domain shift, object tracking, strategic classification). Although most problems are solved in discrete time, the underlying process is often continuous in nature. We exploit this underlying continuity by developing predictor-corrector algorithms for time-varying stochastic optimizations. We provide error bounds for the iterates, both in presence of pure and noisy access to the queries from the relevant derivatives of the loss function. Furthermore, we show (theoretically and empirically in several examples) that our method outperforms non-predictor corrector methods that do not exploit the underlying continuous process.
