• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE Symposium Series on Computational Intelligence >Learning deep models of optimization landscapes
【24h】

Learning deep models of optimization landscapes

机译：学习优化景观的深入模型

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependences between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly modeling the interactions between sets of parameters and the overall quality of the solutions discovered. We demonstrate a novel method, based on learning deep networks, to model the global landscapes of optimization problems. To represent the search space concisely and accurately, the deep networks must encode information about the underlying parameter interactions and their contributions to the quality of the solution. Once the networks are trained, the networks are probed to reveal parameter combinations with high expected performance with respect to the optimization task. These estimates are used to initialize fast, randomized, local-search algorithms, which in turn expose more information about the search space that is subsequently used to refine the models. We demonstrate the technique on multiple problems that have arisen in a variety of real-world domains, including: packing, graphics, job scheduling, layout and compression. Strengths, limitations, and extensions of the approach are extensively discussed and demonstrated.
机译：除了最琐碎的优化问题外，解决方案的结构在输入参数之间表现出复杂的相互依存关系。使用随机搜索技术进行的数十年研究表明，对参数集与发现的解决方案的整体质量之间的交互进行显式建模的好处。我们展示了一种基于学习深度网络的新颖方法，可以对优化问题的全球格局进行建模。为了简洁，准确地表示搜索空间，深度网络必须对有关基础参数交互及其对解决方案质量的贡献的信息进行编码。一旦对网络进行了训练，就可以对网络进行探测，以揭示针对优化任务具有较高预期性能的参数组合。这些估计值用于初始化快速，随机的本地搜索算法，该算法继而提供有关搜索空间的更多信息，这些信息随后用于改进模型。我们将针对在现实世界中出现的多个问题演示该技术，这些问题包括：打包，图形，作业计划，布局和压缩。对该方法的优点，局限性和扩展性进行了广泛的讨论和论证。

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