Exponential escape efficiency of SGD from sharp minima in non-stationary regime
We show that stochastic gradient descent (SGD) escapes from sharp minima exponentially fast even before SGD reaches stationary distribution. SGD has been a de-facto standard training algorithm for various machine learning tasks. However, there still exists an open question as to why SGDs find highly generalizable parameters from non-convex target functions, such as the loss function of neural networks. An "escape efficiency" has been an attractive notion to tackle this question, which measures how SGD efficiently escapes from sharp minima with potentially low generalization performance. Despite its importance, the notion has the limitation that it works only when SGD reaches a stationary distribution after sufficient updates. In this paper, we develop a new theory to investigate escape efficiency of SGD with Gaussian noise, by introducing the Large Deviation Theory for dynamical systems. Based on the theory, we prove that the fast escape form sharp minima, named exponential escape, occurs in a non-stationary setting, and that it holds not only for continuous SGD but also for discrete SGD. A key notion for the result is a quantity called "steepness," which describes the SGD's stochastic behavior throughout its training process. Our experiments are consistent with our theory.
Code (1)
Tasks
Open-Ended Question AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dynamic of Stochastic Gradient Descent with State-Dependent Noise
Stochastic gradient descent (SGD) and its variants are mainstream methods to train deep neural networks. Since neural networks are non-convex, more and more works study the dynamic behavior of SGD and the impact to its g…
A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima
Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training deep networks in practice. SGD is known to find a flat minimum with a large neighboring region in the parameter space from which each…
Stochastic OptimizationHow to Escape Saddle Points Efficiently
This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension (i.e., it is almost "dimension-free"). T…
On the diffusion approximation of nonconvex stochastic gradient descent
We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD…
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
Sharpness-Aware Minimization (SAM) has substantially improved the generalization of neural networks under various settings. Despite the success, its effectiveness remains poorly understood. In this work, we discover an i…