SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.10412 · ICLR · 2021

Randomized Automatic Differentiation

Alex Beatson, Ryan Adams, Deniz Oktay, Nick Mcgreivy, Joshua Aduol

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2007.10412.json · badge: /api/ran/2007.10412.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
PrincetonLIPS/RandomizedAutomaticDifferentiation marked official in Papers with Code
Papers with Code archive
5 ran · 1 no recorded run
FunctionStatusWhere it lives
RandMatMul Ran
ran on a synthesized input · constructed an object; no result was computed
PrincetonLIPS/RandomizedAutomaticDifferentiation/nn_experiments/layers.py
pointer only (licence: NONE) · get_code("d3cd29817cd4d4a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/RandomizedAutomaticDifferentiation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

input2rp Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/RandomizedAutomaticDifferentiation/nn_experiments/layers.py
pointer only (licence: NONE) · get_code("011593930f493777")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/RandomizedAutomaticDifferentiation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

input2sparse Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/RandomizedAutomaticDifferentiation/nn_experiments/layers.py
pointer only (licence: NONE) · get_code("df32b9088bcce9cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/RandomizedAutomaticDifferentiation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rp2input Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/RandomizedAutomaticDifferentiation/nn_experiments/layers.py
pointer only (licence: NONE) · get_code("ad2ed72469a87d5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/RandomizedAutomaticDifferentiation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sparse2input Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/RandomizedAutomaticDifferentiation/nn_experiments/layers.py
pointer only (licence: NONE) · get_code("a837f5581550d190")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/RandomizedAutomaticDifferentiation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RandLinear Not yet run
unverified (harvested, no recorded run)
PrincetonLIPS/RandomizedAutomaticDifferentiation/nn_experiments/layers.py
pointer only (licence: NONE) · get_code("63e3e2ef9222f31a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/RandomizedAutomaticDifferentiation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

The successes of deep learning, variational inference, and many other fields have been aided by specialized implementations of reverse-mode automatic differentiation (AD) to compute gradients of mega-dimensional objectives. The AD techniques underlying these tools were designed to compute exact gradients to numerical precision, but modern machine learning models are almost always trained with stochastic gradient descent. Why spend computation and memory on exact (minibatch) gradients only to use them for stochastic optimization? We develop a general framework and approach for randomized automatic differentiation (RAD), which can allow unbiased gradient estimates to be computed with reduced memory in return for variance. We examine limitations of the general approach, and argue that we must leverage problem specific structure to realize benefits. We develop RAD techniques for a variety of simple neural network architectures, and show that for a fixed memory budget, RAD converges in fewer iterations than using a small batch size for feedforward networks, and in a similar number for recurrent networks. We also show that RAD can be applied to scientific computing, and use it to develop a low-memory stochastic gradient method for optimizing the control parameters of a linear reaction-diffusion PDE representing a fission reactor.

For agents

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

get_harvested_code_for_paper("2007.10412")
get_code_for_paper("2007.10412")
have("2007.10412")

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

curl https://syntology.ai/api/ran/2007.10412.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.10412.svg)](https://syntology.ai/paper/2007.10412)

Connect an agent — have() is free.