论文标题

副本对称自由能的minimax公式

Minimax formula for the replica symmetric free energy of deep restricted Boltzmann machines

论文作者

Genovese, Giuseppe

论文摘要

我们研究了最常用的深层建筑的自由能,用于有限的玻尔兹曼机器,该机器串联处置了层。假设独立的高斯分布式随机权重,我们表明所谓的复制副本中的误差项可以优化为鞍点。这使我们猜想在复制品对称近似中,自由能由min max公式给出,这与两层案例相同。

We study the free energy of a most used deep architecture for restricted Boltzmann machines, where the layers are disposed in series. Assuming independent Gaussian distributed random weights, we show that the error term in the so-called replica symmetric sum rule can be optimised as a saddle point. This leads us to conjecture that in the replica symmetric approximation the free energy is given by a min max formula, which parallels the one achieved for two-layer case.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源