This work presents the first projection-free algorithm to solve stochastic bi-level optimization problems, where the objective function depends on the solution of another stochastic optimization problem. The proposed $\textbf{S}$tochastic $\textbf{Bi}$-level $\textbf{F}$rank-$\textbf{W}$olfe ($\textbf{SBFW}$) algorithm can be applied to streaming settings and does not make use of large batches or checkpoints. The sample complexity of SBFW is shown to be $\mathcal{O}(\epsilon^{-3})$ for convex objectives and $\mathcal{O}(\epsilon^{-4})$ for non-convex objectives. Improved rates are derived for the stochastic compositional problem, which is a special case of the bi-level problem, and entails minimizing the composition of two expected-value functions. The proposed $\textbf{S}$tochastic $\textbf{C}$ompositional $\textbf{F}$rank-$\textbf{W}$olfe ($\textbf{SCFW}$) is shown to achieve a sample complexity of $\mathcal{O}(\epsilon^{-2})$ for convex objectives and $\mathcal{O}(\epsilon^{-3})$ for non-convex objectives, at par with the state-of-the-art sample complexities for projection-free algorithms solving single-level problems. We demonstrate the advantage of the proposed methods by solving the problem of matrix completion with denoising and the problem of policy value evaluation in reinforcement learning.
翻译:这项工作提出了解决双级优化问题的首个无投影算法, 其目标功能取决于另一个随机优化问题的解决方案 。 拟议的 $\ textbf{ bi} 美元 $\ textbf{ bi} 美元 美元 $\ textbf{ W} F} 美元 美元 美元 美元 美元 用于流流学设置, 不使用大批量或检查点 。 SBFW 的抽样复杂度显示为 $\ mathal{ O} (\ epsilon_ 3} 3} 美元 。 用于 comvex 目标和 $\ textb} 非colflegal 的 价格。 用于双级问题的一个特殊案例, 并意味着将两个预期值功能的构成最小化 。 以 $\ textff} 美元 和 美元=Flational=x 目标的稳定性在 $_\\\\\ texx 美元 美元 里, 显示 liglevel=x levelal_ level level lement lement level level level level lemental=x $=x $=x $=xxxxxxxxxxxxxxxxxxx leg=xx legal=x leg=x ==x =x =x =xxxxxxxxxx =x =x =x 。