SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1502.03492 · 2015

Gradient-based Hyperparameter Optimization through Reversible Learning

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

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters by chaining derivatives backwards through the entire training procedure. These gradients allow us to optimize thousands of hyperparameters, including step-size and momentum schedules, weight initialization distributions, richly parameterized regularization schemes, and neural network architectures. We compute hyperparameter gradients by exactly reversing the dynamics of stochastic gradient descent with momentum.

For agents

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

get_harvested_code_for_paper("1502.03492")
get_code_for_paper("1502.03492")
have("1502.03492")

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

curl https://syntology.ai/api/ran/1502.03492.json

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

[![Syntology run record](https://syntology.ai/api/ran/1502.03492.svg)](https://syntology.ai/paper/1502.03492)

Connect an agent — have() is free.