Pith. sign in

Paper Citation Record · LEDGER

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature

As of 10 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2510.05416.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2510.05416 v3

Coverage vector

measured 60 of 60 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T11:24:35.177585Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

60 of 60 outbound references displayed

  • verified exact2
  • verified fuzzy0
  • unresolved58
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bfe649a0-4b89-4ef7-9b0e-3292c33474a6 · outbound

This paper cites write newline.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.241422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.241422Z digest=sha256:01a16b513e9d2b075f39a5c64130e7ce5f93153d24be44752d3650ae1f06bd9a

Observation 17151b5c-eb06-48ed-b5a1-b01aae5d2754 · outbound

This paper cites @esa (Ref.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature @esa (Ref

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.388611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.388611Z digest=sha256:cc577b2e419d8ed47034392b8ad43279c3c4fb4bd246c733a4a59f55dbee0eb2

Observation 0c7a7e0e-b903-4e2c-8fca-61809f3dee10 · outbound

This paper cites an unresolved cited work.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Unresolved cited work

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.509018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.509018Z digest=sha256:5f77af54b4ca40010d30a7a5a9e097496814f2435406f5fe644e0e0a95898299

Observation 608af4d8-2b4f-4d1a-9e6a-37241e19faea · outbound

This paper cites an unresolved cited work.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.622573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.622573Z digest=sha256:726df7ca46f6c0cddec18e4e6267a83e45658ca34d66589269a0934bf1f0083a

Observation 4be31fe4-9831-4482-b45b-867fae55b147 · outbound

This paper cites Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.724786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.724786Z digest=sha256:0e45e9b4098a5189d7e8c807f172c09c5594f328b26b2290138b61ad71d86169

Observation 1d070509-66f0-4dfd-8c97-4076c6c6bd20 · outbound

This paper cites Optuna: A next-generation hyperparameter optimization framework.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Optuna: A next-generation hyperparameter optimization framework

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.837087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.837087Z digest=sha256:13e355b259a8e6fcefdc24d3e42ca24f08922fe12347c3e4c8f33bc8d1161157

Observation 38e17871-b955-442f-9382-26c761214fda · outbound

This paper cites Privacy amplification via random check-ins.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Privacy amplification via random check-ins

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:29.953811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:29.953811Z digest=sha256:06090366169f09fa248069a37010608f1e36a04d5eed326d21f737e3d03554c5

Observation 05d507c0-47d9-49cc-87b4-73dadd11e9f4 · outbound

This paper cites Automatic clipping: Differentially private deep learning made easier and stronger.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Automatic clipping: Differentially private deep learning made easier and stronger

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.047021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.047021Z digest=sha256:9ae4886df9ad8fde0d596f2109af026f8b232e9d86255ef844d2b6f64976fd3f

Observation c3e2cd5e-fee6-48d4-ba4b-69e7b20dc705 · outbound

This paper cites Differentially private optimization on large model at small cost.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Differentially private optimization on large model at small cost

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.166278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.166278Z digest=sha256:76e24bbb485335b7d1dce51c62188368fcfad02ae9f16276058d110059c3685f

Observation 86645036-d508-4ec6-8038-613c07d31c33 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature A simple framework for contrastive learning of visual representations

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.289138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.289138Z digest=sha256:9ae3f322aa0ee77fe0a1635be34577377e508b1cba86cbafb97721b404c69bcd

Observation f6887b68-e742-42de-bdd9-d60ac3077ec6 · outbound

This paper cites Choquette-Choo, Arun Ganesh, Ryan McKenna, Hugh Brendan McMahan, J Keith Rush, Abhradeep Guha Thakurta, and Zheng Xu.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Choquette-Choo, Arun Ganesh, Ryan McKenna, Hugh Brendan McMahan, J Keith Rush, Abhradeep Guha Thakurta, and Zheng Xu

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.380448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.380448Z digest=sha256:1ffb969235b3552e5abd23cddb5606064b6ab96bcf831ab0621039ccf5a458ec

Observation 81362f9e-ad4e-4ec8-8653-f56adfdf192d · outbound

This paper cites Choquette-Choo, H.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Choquette-Choo, H

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.500960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.500960Z digest=sha256:bc3f901a0041686d7aa3e8f6729aaaf8ccb42f983f9216ff40b9ac841f58d5cb

Observation 2dfbea16-0d05-4d4e-8c08-23985a47b764 · outbound

This paper cites Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.658161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.658161Z digest=sha256:3d43e81db1585d35ef84e6f951d561199b255f2e7417a62777afdb31fc8d8580

Observation 9863961d-59f2-4548-a21a-a06a5c458366 · outbound

This paper cites Scalable DP - SGD : Shuffling vs.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Scalable DP - SGD : Shuffling vs

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:30.815989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:30.815989Z digest=sha256:bf528cd694407a18da1ca70bf13f1171741fad44aa28b4177936300749d0e2dc

Observation d5b44236-8306-4ac9-9af4-9c7d873f8b74 · outbound

This paper cites Unlocking High-Accuracy Differentially Private Image Classification through Scale.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Unlocking High-Accuracy Differentially Private Image Classification through Scale

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.040676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.040676Z digest=sha256:30ce8ce8c491f6244e19b2c81e4917586bd3258e5769cbde36bfa2be60965fb8

Observation 5ba0fd1f-f75e-4f8c-ba0d-4cb91f71b7a3 · outbound

This paper cites Brendan McMahan, John Rush, Adam Smith, and Abhradeep Guha Thakurta.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Brendan McMahan, John Rush, Adam Smith, and Abhradeep Guha Thakurta

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.205056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.205056Z digest=sha256:d725bf742890500f44aebcb806b42e4a220f6807a4f8f32e322f00b6e8e17ca1

Observation 343fa02b-6c4d-4542-b48e-abdf452d32ca · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.299162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.299162Z digest=sha256:cb596a2e203b8b0c8aa799398e99e5148ed598154905333e214fa1eae735e510

Observation 704edaaa-e94f-44ff-af23-706364860411 · outbound

This paper cites Brendan McMahan, Krishna Pillutla, Thomas Steinke, and Abhradeep Thakurta.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Brendan McMahan, Krishna Pillutla, Thomas Steinke, and Abhradeep Thakurta

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.398159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.398159Z digest=sha256:c1b6ad8114419b914775e28651680a0a3182a4e1b426243a7a564b80618fd88b

Observation 73eb1380-4d53-476a-aa6b-cd2b4ce78758 · outbound

This paper cites Our data, ourselves: privacy via distributed noise generation.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Our data, ourselves: privacy via distributed noise generation

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.537051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.537051Z digest=sha256:f618b95d9d67b0ee269d1cdb091b18c68e97fc4f69d48093c26609ebf36dc47e

Observation f130df97-dcc7-4837-8b3d-3d0f8dc2536c · outbound

This paper cites Calibrating noise to sensitivity in private data analysis.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Calibrating noise to sensitivity in private data analysis

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.635219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.635219Z digest=sha256:d17cef424d01bff2cc1c31bbb955e977c3b149f31247db94c099bb68da40bb44

Observation a1d21012-e0b3-4ac3-8d0e-417dd36c7fdd · outbound

This paper cites Privacy amplification by random allocation, 2025.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Privacy amplification by random allocation, 2025

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.708467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.708467Z digest=sha256:f1ff0cd69e1acbc031ecd4c0fd42ef2782b06fa68f69da64da2da5c96a8d69d8

Observation 98ea5923-2c9b-4541-8ca0-3160edc1d031 · outbound

This paper cites Tighter Privacy Analysis for Truncated Poisson Sampling.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Tighter Privacy Analysis for Truncated Poisson Sampling

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.847095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.847095Z digest=sha256:964eea29d36dec8ea52c3b1817a3b4f990fff2260b9a12175b1028f99658a133

Observation 04ac7765-e962-4201-9277-1873adcaf7da · outbound

This paper cites Faster differentially private convex optimization via second-order methods.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Faster differentially private convex optimization via second-order methods

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:31.938915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:31.938915Z digest=sha256:0e3829be48803cbfc3b274b71ff3d0b9bd64e602b54d747b1cf4d062ceae2328

Observation ad62fae9-781e-453b-b59c-029a82535b80 · outbound

This paper cites On Design Principles for Private Adaptive Optimizers.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature On Design Principles for Private Adaptive Optimizers

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.004653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.004653Z digest=sha256:67d1588314e50f7f388ca0cf3a640c0b8c02614acf65761cf6773047bc6d50f5

Observation 474eb82b-48eb-429c-b295-ca128f81d483 · outbound

This paper cites An investigation into neural net optimization via hessian eigenvalue density.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature An investigation into neural net optimization via hessian eigenvalue density

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.135859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.135859Z digest=sha256:12ef5f12b5c35dd324e9aee5d5c52ca4a1e9c5e224212829b06a76133395f3e7

Observation 3071a16b-fecb-4c16-aedc-c6bf16eea3d8 · outbound

This paper cites Understanding the difficulty of training deep feedforward neural networks.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Understanding the difficulty of training deep feedforward neural networks

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.235142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.235142Z digest=sha256:855b39bf544ba411c52a0961332e27a291aab1448257d9bdab6dd3ef59a3a34d

Observation dce7cce7-a168-4adf-bcff-edfe6eff19fa · outbound

This paper cites G rammarly: F ree A I W riting A ssistance --- grammarly.com.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature G rammarly: F ree A I W riting A ssistance --- grammarly.com

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.296314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.296314Z digest=sha256:97bed86c3f30450371650593e6e3c282faac1039e42b1f1efb895cd3d70b7ac5

Observation 0b05aa2c-5b92-4ed0-88e7-df88d447687d · outbound

This paper cites pfl-research: simulation framework for accelerating research in Private Federated Learning.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature pfl-research: simulation framework for accelerating research in Private Federated Learning

Reference 28

Resolution
verified exact
local_arxiv, observed 2026-08-04T11:28:41.796595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-04T11:24:32.365964Z digest=sha256:6158940ed6ce6a9cd35bb8b126a000c83d074855ec3580e5b95a9fb7c0ddee5e

Observation 6905795c-83f4-4620-b163-9e2ce053e91a · outbound

This paper cites Choosing public datasets for private machine learning via gradient subspace distance.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Choosing public datasets for private machine learning via gradient subspace distance

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.467130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.467130Z digest=sha256:60387ee48358ffdbbd23a3b7708cb3d62ba86671566c19e3752a30f39be6b408

Observation dc105082-fa16-4164-a0a2-107df20d63a9 · outbound

This paper cites Gradient Descent Happens in a Tiny Subspace.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Gradient Descent Happens in a Tiny Subspace

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.545152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.545152Z digest=sha256:00247e3a911aa8e15b9674a788f3ba9b4cddac91a59f6ce6dc0ad10fea48d3d4

Observation d229cf2e-5920-4961-a6a5-c362222f0a23 · outbound

This paper cites Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.598718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.598718Z digest=sha256:8bb236a06a29f6e30a6aaf015b5c19b532a424d0d112942587f3b59564f60556

Observation 3d2249a5-ffb9-454b-a7e5-2a06565cb65a · outbound

This paper cites Deep residual learning for image recognition.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Deep residual learning for image recognition

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.700699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.700699Z digest=sha256:8f03c2bcc13baab4d41a75c5fb40fe20e6a0bca29ddcbd44bb4e60cf38cee3cf

Observation 9b2f51e0-6e86-430e-83ee-1971dd2f857e · outbound

This paper cites Lo RA : Low-rank adaptation of large language models.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Lo RA : Low-rank adaptation of large language models

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.820690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.820690Z digest=sha256:5de211a03571895f631d7f72080fa2501a9c171852c6344e838616003e0e0e07

Observation e537e90a-f7c8-434e-962e-fa477a69df9b · outbound

This paper cites Practical and private (deep) learning without sampling or shuffling.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Practical and private (deep) learning without sampling or shuffling

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:32.919118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:32.919118Z digest=sha256:d5f18eb7b2d4be3f1aedd85d129db5a9d0d67f55dafa79427f3cdb674a054347

Observation 5187198a-5ee5-42f7-9e44-c26d73bcd3a0 · outbound

This paper cites Back to square roots: An optimal bound on the matrix factorization error for multi-epoch differentially private sgd.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Back to square roots: An optimal bound on the matrix factorization error for multi-epoch differentially private sgd

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.014356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.014356Z digest=sha256:8410bb3b2f8eb8d49d358452e76f153eee57b6d9cbb0a5ce393ab89d13efdfdf

Observation b59cb96c-ded3-435f-9eb4-42e60a2a61b3 · outbound

This paper cites Kingma and Jimmy Ba.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Kingma and Jimmy Ba

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.068189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.068189Z digest=sha256:ecaef2691020bb6e0fc1746cb626cdb41355a7cf66091c303fdab35127148b51

Observation dfac3297-3247-44ca-ae21-af53cb8d412c · outbound

This paper cites Gradient descent with linearly correlated noise: theory and applications to differential privacy.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Gradient descent with linearly correlated noise: theory and applications to differential privacy

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.178102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.178102Z digest=sha256:2354e4838bb40e40237f766875f2907c4a9d8b6d9d1af09a1cf1fea8be7d2ccd

Observation 07bc1e56-aef8-4454-b682-be85cc8736ff · outbound

This paper cites Learning multiple layers of features from tiny images.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Learning multiple layers of features from tiny images

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.264736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.264736Z digest=sha256:21119c3787dbb1f53c21d4e9ac04b454ec4d33e45220c2295262477d6be84c8b

Observation 87dfe996-15d5-4851-b1a6-c04e1fc5fa2f · outbound

This paper cites Toward Training at ImageNet Scale with Differential Privacy.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Toward Training at ImageNet Scale with Differential Privacy

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.364120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.364120Z digest=sha256:f85cd0f3a35e4e50f86884f143946839b812f77522d1de898d96c072008e68ca

Observation 5909393c-2bb3-4e77-a952-10a3332ea223 · outbound

This paper cites An iteration method for the solution of the eigenvalue problem of linear differential and integral operators.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature An iteration method for the solution of the eigenvalue problem of linear differential and integral operators

Reference 40

Resolution
verified exact
doi, observed 2026-08-04T11:28:41.523682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=arxiv_source observed=2026-08-04T11:24:33.428658Z digest=sha256:425b6673171fbd0e5fed44a56539b12ee24929b6ef5fe57588bf16e25c2b756c

Observation 3f89a113-87e2-4c1b-92ca-5f4aa2e9f3a0 · outbound

This paper cites Tiny imagenet visual recognition challenge.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Tiny imagenet visual recognition challenge

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.504013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.504013Z digest=sha256:f8cf8a21eed4f81febd2ce6a6db717e136a17187a0510b974437f7000197dd3a

Observation ab9ac34d-e797-4ee9-ac2f-3401a53c4132 · outbound

This paper cites Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.615818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.615818Z digest=sha256:76cf0612036b16298400096b9f5b86648f6482bcca603bb5674fff503561e5e3

Observation 5a7d49ab-dd10-44d7-be2e-6a8356d14967 · outbound

This paper cites Scaling up differentially private deep learning with fast per-example gradient clipping.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Scaling up differentially private deep learning with fast per-example gradient clipping

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.718287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.718287Z digest=sha256:2ba9615e91e6dd62318565ebbbc437bb945d759709a44b3791d33fafdec825b4

Observation 925f8af5-c28f-473a-b9d8-0bffc31202a4 · outbound

This paper cites Reddi, Hugh Brendan McMahan, and Virginia Smith.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Reddi, Hugh Brendan McMahan, and Virginia Smith

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.782054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.782054Z digest=sha256:471f45428024968defc4068698b4652183f2fa54fb8208ddb250f1ba257b9ad8

Observation a020e88f-e817-4ded-97ed-a1dd74cc6c7f · outbound

This paper cites Large language models can be strong differentially private learners.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Large language models can be strong differentially private learners

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.878436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.878436Z digest=sha256:0fc3d8322a630811981590a89bb93501af4c5dc2dfdba635d2ee2e1c3acf331c

Observation 06e99e9b-45a5-4a52-b0a4-6eb0c1e37988 · outbound

This paper cites Large language models can be strong differentially private learners.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Large language models can be strong differentially private learners

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:33.956754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:33.956754Z digest=sha256:f521ae80c7a0dac35b863d7387d0e1d1e195b50c2c5168365832808ebb61ee50

Observation fd18f392-a251-49be-81cf-605739b8fc91 · outbound

This paper cites An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.046744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.046744Z digest=sha256:087e59f6bd240dbf74c80a894eff53de0c4abc2480f5e026b16613a9ea8c7dc7

Observation 835142fa-1612-4255-bb70-30058ccdecd1 · outbound

This paper cites an unresolved cited work.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Unresolved cited work

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.150081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.150081Z digest=sha256:e35a66a912d3ab8fbf21eb158b6fd19460859a61fb4bde81e6e860dd4e698519

Observation 60defadf-e90c-4d26-a3db-3b46be5df369 · outbound

This paper cites Updating quasi-newton matrices with limited storage.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Updating quasi-newton matrices with limited storage

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.213979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.213979Z digest=sha256:473c90593f557079ca6a9848b9e9bbd9203805bf27d3d33dc47a8a2cd69d4426

Observation 4e61f0d4-561b-40c0-ab6b-d77e8f4e199d · outbound

This paper cites The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.334746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.334746Z digest=sha256:12aaff822ce0156f738501d06ead262d301af84fdc117a849d2a931af5d881f5

Observation 14f8bc4c-d990-42ae-8ccd-7c3cc50a86f6 · outbound

This paper cites PyTorch: an imperative style, high-performance deep learning library.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature PyTorch: an imperative style, high-performance deep learning library

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.408753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.408753Z digest=sha256:5161952d2e4967d6cc2c499c2fd8121c0135540ec66eebb1b4c3b1d44bee4913

Observation 231781b1-9378-4076-bc39-43d37ce3e5ea · outbound

This paper cites Correlated Noise Mechanisms for Differentially Private Learning.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Correlated Noise Mechanisms for Differentially Private Learning

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.503894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.503894Z digest=sha256:535a2fd2667ffdb72b6bc31aa9e683152d2cc02205243a77e8e56a961a80225d

Observation a2ac307c-cc3d-4d9a-9c27-5834c3700537 · outbound

This paper cites Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.558953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.558953Z digest=sha256:0529985c1cd113744a4d8b9ba3a9dff49bcfe2295419ff34fabec64d4e917566

Observation 8b69fa44-3c90-4e10-853a-39764abbd49a · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.626500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.626500Z digest=sha256:4631b750408ba66b3293df7841dd78f1f887d49dab793df5319978667f7e834f

Observation 3041fc00-2d12-448c-b5a1-d95163cb63dd · outbound

This paper cites Deep image prior.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Deep image prior

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.706453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.706453Z digest=sha256:8deb885f238ee848eb207532b99c3c29310a829663e46a205cf8aee3574b1742

Observation 5dfd9c53-2752-4f1b-988d-91da8054a7a1 · outbound

This paper cites Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.810309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.810309Z digest=sha256:2c7acd6fdb1dd4d8d326d91d56d1a52e44b7a17bd408ee6424fd872cc2ab1f60

Observation bc60db6b-6dd5-445b-a16e-5edc69a925ef · outbound

This paper cites Opacus: User-Friendly Differential Privacy Library in PyTorch.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Opacus: User-Friendly Differential Privacy Library in PyTorch

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:34.927555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:34.927555Z digest=sha256:74c5609d356021cabaa2324c9af0563d871e4584f98793b567d93f777af7ef50

Observation beb051bf-bee2-4168-bdf6-0bb78a90f905 · outbound

This paper cites Do not let privacy overbill utility: Gradient embedding perturbation for private learning.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Do not let privacy overbill utility: Gradient embedding perturbation for private learning

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:35.049590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:35.049590Z digest=sha256:d2e5790f37bee677f8b1c33819e360d04d08ed7d29d1711582e1b1373d8da6d5

Observation 9b16f577-3bc3-4104-b567-3621eb513435 · outbound

This paper cites Differentially private fine-tuning of language models.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Differentially private fine-tuning of language models

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:35.123314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:35.123314Z digest=sha256:9dbcf7bbe34041c4e7c6ccbfb3756b13e144d18c2fc548e551a990572314f2cf

Observation 934421a7-477e-44ab-8c58-6764f33511c2 · outbound

This paper cites Bypassing the ambient dimension: Private \ sgd \ with gradient subspace identification.

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature Bypassing the ambient dimension: Private \ sgd \ with gradient subspace identification

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-04T11:24:35.177585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:24:35.177585Z digest=sha256:f89cb0f70f3e861aa5f30408919e5b7b7a7000a2fe997ee9dfd842711b70f134

Pith citing papers

No inbound Pith citation observations are available.