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 0902.3526stat.MLcs.LGmath.STstat.TH
收藏

硬约束条件下的在线多任务学习

Online Multi-task Learning with Hard Constraints

ICREA(加泰罗尼亚研究与高级研究院);Universitat Pompeu Fabra(庞培法布拉大学);Ecole Normale Supérieure(巴黎高等师范学院);CNRS(法国国家科学研究中心);HEC Paris(巴黎高等商学院)

Gabor Lugosi, Omiros Papaspiliopoulos, Gilles Stoltz

摘要:

我们讨论多任务在线学习时,决策者必须同时处理M个任务。任务是相关的,这是通过强加的M元组的决策者采取的行动需要满足一定的约束。我们给出自然的例子,这样的限制,然后讨论一般类的易处理的约束,我们引入计算效率的方式选择行动,基本上是通过减少到一个在线的最短路径问题。我们简要讨论了“跟踪”和“强盗”版本的问题,并以各种方式扩展模型,包括非加性的全球损失和不可数的无限任务集。

英文摘要:

We discuss multi-task online learning when a decision maker has to deal simultaneously with M tasks. The tasks are related, which is modeled by imposing that the M-tuple of actions taken by the decision maker needs to satisfy certain constraints. We give natural examples of such restrictions and then discuss a general class of tractable constraints, for which we introduce computationally efficient ways of selecting actions, essentially by reducing to an on-line shortest path problem. We briefly discuss "tracking" and "bandit" versions of the problem and extend the model in various ways, including non-additive global losses and uncountably infinite sets of tasks.

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。

↑