SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1506.02617 · 2015

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

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

We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with respect to a path-wise regularizer related to max-norm regularization. Path-SGD is easy and efficient to implement and leads to empirical gains over SGD and AdaGrad.

For agents

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

get_harvested_code_for_paper("1506.02617")
get_code_for_paper("1506.02617")
have("1506.02617")

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

curl https://syntology.ai/api/ran/1506.02617.json

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

[![Syntology run record](https://syntology.ai/api/ran/1506.02617.svg)](https://syntology.ai/paper/1506.02617)

Connect an agent — have() is free.