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 cs/0506041cs.LGcs.AI
收藏

具有凸损失函数的竞争在线学习

Competitive on-line learning with a convex loss function

Vladimir Vovk

摘要:

我们考虑不确定性下的序贯决策问题,其中决策造成的损失取决于下面的二元观测。在竞争性在线学习中,目标是设计决策算法,几乎与广泛基准类中的最佳决策规则一样好,而不对观察结果的生成方式做出任何假设。然而,在这一领域的标准算法只能处理有限维(通常是可数的)基准类。在本文中,我们给出了类似的结果,决策规则范围内的任意再生核希尔伯特空间。例如,它表明,对于广泛的损失函数(包括标准平方,绝对和对数损失函数)的主算法的平均损失,在第一$N$意见,不超过最佳决策规则的平均损失与有界范数加$O(N^{-1/2})$。我们的证明技术与标准技术有很大不同,并且基于最近有关防御预测的结果。鉴于防御性预测算法产生的概率,这是众所周知的,从长远来看,有很好的校准和分辨率,我们使用预期损失最小化原则,以找到一个合适的决定。

英文摘要:

We consider the problem of sequential decision making under uncertainty in which the loss caused by a decision depends on the following binary observation. In competitive on-line learning, the goal is to design decision algorithms that are almost as good as the best decision rules in a wide benchmark class, without making any assumptions about the way the observations are generated. However, standard algorithms in this area can only deal with finite-dimensional (often countable) benchmark classes. In this paper we give similar results for decision rules ranging over an arbitrary reproducing kernel Hilbert space. For example, it is shown that for a wide class of loss functions (including the standard square, absolute, and log loss functions) the average loss of the master algorithm, over the first $N$ observations, does not exceed the average loss of the best decision rule with a bounded norm plus $O(N^{-1/2})$. Our proof technique is very different from the standard ones and is based on recent results about defensive forecasting. Given the probabilities produced by a defensive forecasting algorithm, which are known to be well calibrated and to have good resolution in the long run, we use the expected loss minimization principle to find a suitable decision.

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。

↑