arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.03806cs.LGstat.ML
收藏

学习要记住什么

Learning what to remember

University of California, San Diego(加利福尼亚大学圣迭戈分校)

Robi Bhattacharjee, Gaurav Mahajan

摘要:

我们考虑终身学习的情况下,学习者面临着一个永无止境的和任意流的事实,并决定哪些保留在其有限的记忆。我们引入了一个数学模型的基础上的在线学习框架,在该框架中,学习者衡量自己对一组专家,也是记忆约束,并反映不同的政策,要记住什么。穿插在事实流中的是偶然的问题,对于每一个问题,如果学习者没有记住相应的事实,就会产生损失。它的目标是在使用大致相同的内存量的情况下,在事后看来几乎和最好的专家一样好。我们确定困难,在这个内存受限的情况下使用乘法权重更新算法,并设计一个替代方案,其遗憾的保证接近最好的可能。

英文摘要:

We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory. We introduce a mathematical model based on the online learning framework, in which the learner measures itself against a collection of experts that are also memory-constrained and that reflect different policies for what to remember. Interspersed with the stream of facts are occasional questions, and on each of these the learner incurs a loss if it has not remembered the corresponding fact. Its goal is to do almost as well as the best expert in hindsight, while using roughly the same amount of memory. We identify difficulties with using the multiplicative weights update algorithm in this memory-constrained scenario, and design an alternative scheme whose regret guarantees are close to the best possible.

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。

↑