DeepAI AI Chat
Log In Sign Up

On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)

by   Zhiyuan Li, et al.

It is generally recognized that finite learning rate (LR), in contrast to infinitesimal LR, is important for good generalization in real-life deep nets. Most attempted explanations propose approximating finite-LR SGD with Ito Stochastic Differential Equations (SDEs). But formal justification for this approximation (e.g., (Li et al., 2019a)) only applies to SGD with tiny LR. Experimental verification of the approximation appears computationally infeasible. The current paper clarifies the picture with the following contributions: (a) An efficient simulation algorithm SVAG that provably converges to the conventionally used Ito SDE approximation. (b) Experiments using this simulation to demonstrate that the previously proposed SDE approximation can meaningfully capture the training and generalization properties of common deep nets. (c) A provable and empirically testable necessary condition for the SDE approximation to hold and also its most famous implication, the linear scaling rule (Smith et al., 2020; Goyal et al., 2017). The analysis also gives rigorous insight into why the SDE approximation may fail.


page 1

page 2

page 3

page 4


Why (and When) does Local SGD Generalize Better than SGD?

Local SGD is a communication-efficient variant of SGD for large-scale tr...

How Many Factors Influence Minima in SGD?

Stochastic gradient descent (SGD) is often applied to train Deep Neural ...

Improved quantum algorithms for linear and nonlinear differential equations

We present substantially generalized and improved quantum algorithms ove...

What Happens after SGD Reaches Zero Loss? –A Mathematical Framework

Understanding the implicit bias of Stochastic Gradient Descent (SGD) is ...

Compression Implies Generalization

Explaining the surprising generalization performance of deep neural netw...