Skip to yearly menu bar Skip to main content


Poster

Power-Law Escape Rate of SGD

Takashi Mori · Liu Ziyin · Kangqiao Liu · Masahito Ueda

Hall E #1114

Keywords: [ MISC: Supervised Learning ] [ T: Deep Learning ] [ OPT: Stochastic ] [ OPT: Non-Convex ] [ T: Optimization ]


Abstract: Stochastic gradient descent (SGD) undergoes complicated multiplicative noise for the mean-square loss. We use this property of SGD noise to derive a stochastic differential equation (SDE) with simpler additive noise by performing a random time change. Using this formalism, we show that the log loss barrier $\Delta\log L=\log[L(\theta^s)/L(\theta^*)]$ between a local minimum $\theta^*$ and a saddle $\theta^s$ determines the escape rate of SGD from the local minimum, contrary to the previous results borrowing from physics that the linear loss barrier $\Delta L=L(\theta^s)-L(\theta^*)$ decides the escape rate. Our escape-rate formula strongly depends on the typical magnitude $h^*$ and the number $n$ of the outlier eigenvalues of the Hessian. This result explains an empirical fact that SGD prefers flat minima with low effective dimensions, giving an insight into implicit biases of SGD.

Chat is not available.