This work provides test error bounds for iterative fixed point methods on linear predictors -- specifically, stochastic and batch mirror descent (MD), and stochastic temporal difference learning (TD) -- with two core contributions: (a) a single proof technique which gives high probability guarantees despite the absence of projections, regularization, or any equivalents, even when optima have large or infinite norm, for quadratically-bounded losses (e.g., providing unified treatment of squared and logistic losses); (b) locally-adapted rates which depend not on global problem structure (such as condition numbers and maximum margins), but rather on properties of low norm predictors which may suffer some small excess test error. The proof technique is an elementary and versatile coupling argument, and is demonstrated here in the following settings: stochastic MD under realizability; stochastic MD for general Markov data; batch MD for general IID data; stochastic MD on heavy-tailed data (still without projections); stochastic TD on Markov chains (all prior stochastic TD bounds are in expectation).
翻译:这项工作为线性预测器的迭代固定点方法 -- -- 具体而言,是随机和批量镜像下沉(MD)以及随机时间差异学习(TD) -- -- 提供了测试误差界限,其中有两个核心贡献:(a) 单一的证明技术,尽管没有预测、正规化或任何等同物,即使Popima具有大或无限的规范,但对于按二次测距计算的损失(例如,提供对平方和后勤损失的统一处理);(b) 当地适应的费率不取决于全球问题结构(如条件数字和最大幅度),而是取决于低标准预测器的特性,这些特性可能遭受一些小的超量测试错误。 证明技术是一种基本和多功能的混合论证,在以下环境中展示:可变性测MD;通用Markov数据的随机MD;通用ID数据的批MD;重尾数据中的随机M(仍然没有预测); Markov 链上的随机TD(所有先前的蒸发式TD框都是预期的)。