We consider the problem of learning a target probability distribution over aset of $N$ binary variables from the knowledge of the expectation values (withthis target distribution) of $M$ observables, drawn uniformly at random. Thespace of all probability distributions compatible with these $M$ expectationvalues within some fixed accuracy, called version space, is studied. Weintroduce a biased measure over the version space, which gives a boostincreasing exponentially with the entropy of the distributions and with anarbitrary inverse `temperature' $\Gamma$. The choice of $\Gamma$ allows us tointerpolate smoothly between the unbiased measure over all distributions in theversion space ($\Gamma=0$) and the pointwise measure concentrated at themaximum entropy distribution ($\Gamma \to \infty$). Using the replica method wecompute the volume of the version space and other quantities of interest, suchas the distance $R$ between the target distribution and the center-of-massdistribution over the version space, as functions of $\alpha=(\log M)/N$ and$\Gamma$ for large $N$. Phase transitions at critical values of $\alpha$ arefound, corresponding to qualitative improvements in the learning of the targetdistribution and to the decrease of the distance $R$. However, for fixed$\alpha$, the distance $R$ does not vary with $\Gamma$, which means that themaximum entropy distribution is not closer to the target distribution than anyother distribution compatible with the observable values. Our results areconfirmed by Monte Carlo sampling of the version space for small system sizes($N\le 10$).
展开▼
机译:我们考虑这样的问题,即从对$ M $可观察值的期望值(具有该目标分布)的知识中随机地得出,从而在$ N $二元变量集合上学习目标概率分布。研究了在一定的固定精度内与这些$ M $期望值兼容的所有概率分布的空间,称为版本空间。我们在版本空间上引入了一个有偏差的度量,它随着分布的熵以及任意的逆温度“ $ \ Gamma $”而呈指数增长。 $ \ Gamma $的选择使我们能够在转换空间中所有分布的无偏测度($ \ Gamma = 0 $)和集中于最大熵分布($ \ Gamma \ to \ infty $)的逐点测度之间进行平滑插值。使用复制方法,我们根据$ \ alpha =(\ log M的函数,计算版本空间的容量和其他感兴趣的数量,例如目标分布与版本空间上的质心分布之间的距离$ R $。 )/ N $和$ \ Gamma $表示较大的$ N $。发现临界值为$ \ alpha $的相变,对应于目标分布学习中的质性改进和距离$ R $的减小。但是,对于固定的$ \ alpha $,距离$ R $不会随$ \ Gamma $的变化而变化,这意味着最大熵分布并不比任何与可观察值兼容的其他分布更接近目标分布。我们的结果得到了较小系统尺寸($ N \ le 10 $)版本空间的蒙特卡洛采样的确认。
展开▼