首页> 外文期刊>Information Theory, IEEE Transactions on >Random-Walk Perturbations for Online Combinatorial Optimization
【24h】

Random-Walk Perturbations for Online Combinatorial Optimization

机译:在线组合优化的随机游走扰动

获取原文
获取原文并翻译 | 示例
           

摘要

We study online combinatorial optimization problems that a learner is interested in minimizing its cumulative regret in the presence of switching costs. To solve such problems, we propose a version of the follow-the-perturbed-leader algorithm in which the cumulative losses are perturbed by independent symmetric random walks. In the general setting, our forecaster is shown to enjoy near-optimal guarantees on both quantities of interest, making it the best known efficient algorithm for the studied problem. In the special case of prediction with expert advice, we show that the forecaster achieves an expected regret of the optimal order , where is the time horizon and is the number of experts, while guaranteeing that the predictions are switched at most times, in expectation.
机译:我们研究在线组合优化问题,学习者有兴趣在出现转换成本的情况下最大程度地减少其累积后悔。为了解决这些问题,我们提出了一种跟随扰动的领导算法,其中累积损失受到独立对称随机游动的扰动。在一般情况下,我们的预测器显示出对两个关注量均具有近乎最优的保证,这使其成为研究问题的最有效算法。在具有专家意见的特殊预测情况下,我们显示出预测者达到了最佳阶的预期后悔,其中Horizo​​n是时间范围,是专家人数,同时保证了预期中的大多数时间都在切换预测。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号