SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09352 · ICML · 2021

Large Scale Private Learning via Low-rank Reparametrization

Tie-Yan Liu, Wei Chen, Da Yu, Huishuai Zhang, Jian Yin

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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; 3 failures of our instrument; 4 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/2106.09352.json · badge: /api/ran/2106.09352.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
dayu11/Differentially-Private-Deep-Learning marked official in Papers with Code
Papers with Code archive
4 ran · 4 no recorded run
FunctionStatusWhere it lives
LrkConv2d Ran
ran on a synthesized input · constructed an object; no result was computed
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("ca59b90ba970fcda")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("d075692ad1036499")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("6e6cd72f51ebc400")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

weight_decomposition Ran
ran; our contract draft was wrong, not the code
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("b6b42d33ba802e1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

ConvBackwardHook Not yet run
unverified (harvested, no recorded run)
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("f99fafb1402a6e8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

ConvFowardHook Not yet run
unverified (harvested, no recorded run)
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("44f4381827c7be33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

_compute_conv_grad_sample Not yet run
unverified (harvested, no recorded run)
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("ef5092f0e5bd3563")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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.

orthogonalize Not yet run
unverified (harvested, no recorded run)
dayu11/Differentially-Private-Deep-Learning/vision/RGP/models/resnet_cifar.py
pointer only (licence: NONE) · get_code("18baa6e835949a4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dayu11/Differentially-Private-Deep-Learning 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence. Specifically, we reparametrize each weight matrix with two gradient-carrier matrices of small dimension and a residual weight matrix. We argue that such reparametrization keeps the forward/backward process unchanged while enabling us to compute the projected gradient without computing the gradient itself. To learn with differential privacy, we design reparametrized gradient perturbation (RGP) that perturbs the gradients on gradientcarrier matrices and reconstructs an update for the original weight from the noisy gradients. Importantly, we use historical updates to find the gradient-carrier matrices, whose optimality is rigorously justified under linear regression and empirically verified with deep learning tasks. RGP significantly reduces the memory cost and improves the utility. For example, we are the first able to apply differential privacy on the BERT model and achieve an average accuracy of 83.9% on four downstream tasks with = 8, which is within 5% loss compared to the non-private baseline but enjoys much lower privacy leakage risk.

For agents

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

get_harvested_code_for_paper("2106.09352")
get_code_for_paper("2106.09352")
have("2106.09352")

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

curl https://syntology.ai/api/ran/2106.09352.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09352.svg)](https://syntology.ai/paper/2106.09352)

Connect an agent — have() is free.