We study the task of finding good local optima in combinatorial optimization problems. Although combinatorial optimization is NP-hard in general, locally optimal solutions are frequently used in practice. Local search methods however typically converge to a limited set of optima that depend on their initialization. Sampling methods on the other hand can access any valid solution, and thus can be used either directly or alongside methods of the former type as a way for finding good local optima. Since the effectiveness of this strategy depends on the sampling distribution, we derive a robust learning algorithm that adapts sampling distributions towards good local optima of arbitrary objective functions. As a first use case, we empirically study the efficiency in which sampling methods can recover locally maximal cliques in undirected graphs. Not only do we show how our adaptive sampler outperforms related methods, we also show how it can even approach the performance of established clique algorithms. As a second use case, we consider how greedy algorithms can be combined with our adaptive sampler, and we demonstrate how this leads to superior performance in k-medoid clustering. Together, these findings suggest that our adaptive sampler can provide an effective strategy to combinatorial optimization problems that arise in practice.
Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints
University of Victoria(维多利亚大学);Southeast University(东南大学);Harbin Institute of Technology(哈尔滨工业大学)
研究了具有长期公平性约束的组合睡眠多臂半强盗问题~(CSMAB-F)。针对该问题,采用Thompson Sampling~(TS)方法最大化总报酬,采用虚拟队列技术处理公平性约束,并设计了一种算法\emph{TS with beta priors and Bernoulli likelihoods for CSMAB-F~(TSCSF-B)}。进一步,我们证明了TSCSF-B能满足公平性约束,并且时间平均后悔的上界为$\frac{N}{2η} + O\left(\frac{\sqrt{mNT\ln T}}{T}\right)$,其中$N$是总的手臂数,$m$是每轮中能同时拉动的最大手臂数~(基数约束),$η$是公平性与奖励的权衡参数.通过放松公平性约束(即,令$η\rightarrow \infty$),该界归结为组合睡眠多臂半强盗问题TS算法的第一个与问题无关的界。最后,我们进行了数值实验,并使用一个高收视率的电影推荐应用程序,以显示所提出的算法的有效性和效率。
When Combinatorial Thompson Sampling meets Approximation Regret
Idemia(亿达美)
研究了近似后悔条件下组合多臂强盗问题的组合Thompson抽样策略。虽然CTS吸引了很多人的兴趣,但它有一个缺点,这是其他常见的CMAB策略在考虑非精确预言时所没有的:对于某些预言,CTS具有较差的近似遗憾(与时间范围$T$线性缩放)[Wang和Chen,2018]。然后,有必要进行研究,以区分CTS可以学习的神谕。该研究由Kong et al. [2021]开始:他们给出了贪婪预言机CTS的一次近似后悔分析,获得了$\mathcal{O}(\log(T)/Δ^2)$阶的上界,其中$Δ$是某个最小奖励差距。在本文中,我们的目标是推动这项研究进一步比简单的情况下,贪婪的甲骨文。我们提供了第一个$\mathcal{O}(\log(T)/Δ)$近似遗憾的上限CTS,在一个特定的条件下获得的近似甲骨文,允许减少到确切的甲骨文分析。因此,我们把这个条件称为REDUCE2EXACT,并观察到它在许多具体的例子中得到满足。此外,它可以扩展到概率触发的武器设置,从而捕获更多的问题,如在线影响最大化。
Entropy-Guided Sampling of Flat Modes in Discrete Spaces
Department of Computer Science, College of Science & College of Engineering, Purdue University(计算机科学系、科学与工程学院、普渡大学);Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Duke University(生物统计学与生物信息学系、杜克大学医学学院、杜克大学)
Stochastic Primal Dual Coordinate Method with Non-Uniform Sampling Based on Optimality Violations
Nagoya Institute of Technology(名古屋工业大学);RIKEN Center for Advanced Intelligence Project(理化学研究所革新智能综合研究中心);National Institute for Materials Science(国立材料科学研究所)