SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00428 · NeurIPS · 2021

Storchastic: A Framework for General Stochastic Automatic Differentiation

Jakub Tomczak, Emile Van Krieken

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

Modelers use automatic differentiation (AD) of computation graphs to implement complex deep learning models without defining gradient computations. Stochastic AD extends AD to stochastic computation graphs with sampling steps, which arise when modelers handle the intractable expectations common in reinforcement learning and variational inference. However, current methods for stochastic AD are limited: They are either only applicable to continuous random variables and differentiable functions, or can only use simple but high variance score-function estimators. To overcome these limitations, we introduce Storchastic, a new framework for AD of stochastic computation graphs. Storchastic allows the modeler to choose from a wide variety of gradient estimation methods at each sampling step, to optimally reduce the variance of the gradient estimates. Furthermore, Storchastic is provably unbiased for estimation of any-order gradients, and generalizes variance reduction techniques to any-order derivative estimates. Finally, we implement Storchastic as a PyTorch library at github.com/HEmile/storchastic.

For agents

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

get_harvested_code_for_paper("2104.00428")
get_code_for_paper("2104.00428")
have("2104.00428")

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

curl https://syntology.ai/api/ran/2104.00428.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.00428.svg)](https://syntology.ai/paper/2104.00428)

Connect an agent — have() is free.