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/0301014cs.LGcs.AImath.PR
收藏

贝叶斯序列预测的收敛性和损失界

Convergence and Loss Bounds for Bayesian Sequence Prediction

Marcus Hutter

摘要:

如果序列$x_1x_2x_3...$的真实生成分布$μ$已知,则可以用贝叶斯规则计算在给定过去观测值$x_1...x_{t-1}$的情况下在时间$t$观测到$x_t$的概率。如果$μ$是未知的,但已知属于类$M$,则可以将预测基于贝叶斯混合$ξ$,该贝叶斯混合$ξ$定义为分布的加权和$ν\in M$。各种收敛结果的混合后$ξ_t$真正的后$μ_t$。特别是一个新的(初等)推导的收敛$ξ_t/μ_t\to 1$提供,它另外给出了收敛速度。允许通用序列预测器基于$x_1...x_{t-1}$选择动作$y_t$,并且如果$x_t$是序列的下一个符号,则接收丢失$\ell_{x_t y_t}$。对$\ell$(除了有界)和$M$的结构没有任何假设。定义了基于混合$ξ$的贝叶斯最优预测方案$Λ_ξ$和贝叶斯最优有信预测方案$Λ_μ$,并证明了$Λ_ξ$的总损失$L_ξ$关于$Λ_μ$的总损失$L_μ$有界.证明了$L_ξ$对于有界$L_μ$是有界的,$L_ξ/L_μ\to 1$对于$L_μ\to \infty$是有界的.瞬时损失的收敛性也被证明。

英文摘要:

The probability of observing $x_t$ at time $t$, given past observations $x_1...x_{t-1}$ can be computed with Bayes' rule if the true generating distribution $μ$ of the sequences $x_1x_2x_3...$ is known. If $μ$ is unknown, but known to belong to a class $M$ one can base ones prediction on the Bayes mix $ξ$ defined as a weighted sum of distributions $ν\in M$. Various convergence results of the mixture posterior $ξ_t$ to the true posterior $μ_t$ are presented. In particular a new (elementary) derivation of the convergence $ξ_t/μ_t\to 1$ is provided, which additionally gives the rate of convergence. A general sequence predictor is allowed to choose an action $y_t$ based on $x_1...x_{t-1}$ and receives loss $\ell_{x_t y_t}$ if $x_t$ is the next symbol of the sequence. No assumptions are made on the structure of $\ell$ (apart from being bounded) and $M$. The Bayes-optimal prediction scheme $Λ_ξ$ based on mixture $ξ$ and the Bayes-optimal informed prediction scheme $Λ_μ$ are defined and the total loss $L_ξ$ of $Λ_ξ$ is bounded in terms of the total loss $L_μ$ of $Λ_μ$. It is shown that $L_ξ$ is bounded for bounded $L_μ$ and $L_ξ/L_μ\to 1$ for $L_μ\to \infty$. Convergence of the instantaneous losses are also proven.

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。

↑