SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.09779 · 2020

Stochasticity in Neural ODEs: An Empirical Study

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Stochastic regularization of neural networks (e.g. dropout) is a wide-spread technique in deep learning that allows for better generalization. Despite its success, continuous-time models, such as neural ordinary differential equation (ODE), usually rely on a completely deterministic feed-forward operation. This work provides an empirical study of stochastically regularized neural ODE on several image-classification tasks (CIFAR-10, CIFAR-100, TinyImageNet). Building upon the formalism of stochastic differential equations (SDEs), we demonstrate that neural SDE is able to outperform its deterministic counterpart. Further, we show that data augmentation during the training improves the performance of both deterministic and stochastic versions of the same model. However, the improvements obtained by the data augmentation completely eliminate the empirical gains of the stochastic regularization, making the difference in the performance of neural ODE and neural SDE negligible.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.09779")
get_code_for_paper("2002.09779")
have("2002.09779")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2002.09779.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2002.09779.svg)](https://syntology.ai/paper/2002.09779)

Connect an agent — have() is free.