arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.01077cs.LG
收藏

带预测(与不带预测)的约束在线两阶段随机优化算法

Constrained Online Two-stage Stochastic Optimization: Algorithm with (and without) Predictions

Hong Kong University of Science and Technology(香港科技大学)

Piao Hu, Jiashuo Jiang, Guodong Lyu, Hao Su

AI总结:

针对具有长期约束的在线两阶段随机优化问题,基于对抗学习算法框架开发了在线优化算法,并分别在有机器学习预测和无预测的场景下提出了新算法及相应的遗憾界。

摘要:

我们考虑在 $T$ 个周期的有限时间跨度内,具有长期约束的在线两阶段随机优化问题。在每个周期,我们采取第一阶段行动,观察模型参数的实现值,然后从依赖于第一阶段决策和模型参数的可行集中采取第二阶段行动。我们的目标是最小化累积目标值,同时保证长期平均的第二阶段决策属于某个集合。我们从对抗学习算法出发,为该在线两阶段问题开发了在线算法。此外,我们算法的遗憾界可以归约为所嵌入的对抗学习算法的遗憾界。基于此框架,我们在各种设置下获得了新结果。当模型参数从未知的非平稳分布中抽取,且我们拥有关于这些分布的机器学习预测时,我们基于该框架开发了一种新算法,其遗憾界为 $O(W_T+\sqrt{T})$,其中 $W_T$ 衡量机器学习预测的总误差。随后,我们开发了另一种在没有机器学习预测时适用的算法,并展示了其性能。

英文摘要:

We consider an online two-stage stochastic optimization with long-term constraints over a finite horizon of $T$ periods. At each period, we take the first-stage action, observe a model parameter realization and then take the second-stage action from a feasible set that depends both on the first-stage decision and the model parameter. We aim to minimize the cumulative objective value while guaranteeing that the long-term average second-stage decision belongs to a set. We develop online algorithms for the online two-stage problem from adversarial learning algorithms. Also, the regret bound of our algorithm can be reduced to the regret bound of embedded adversarial learning algorithms. Based on this framework, we obtain new results under various settings. When the model parameters are drawn from unknown non-stationary distributions and we are given machine-learned predictions of the distributions, we develop a new algorithm from our framework with a regret $O(W_T+\sqrt{T})$, where $W_T$ measures the total inaccuracy of the machine-learned predictions. We then develop another algorithm that works when no machine-learned predictions are given and show the performances.

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。

↑