What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity | Paper Citation Record

Observation 5333c85c-15d2-480e-8d71-a1f24e0b6cf0 · outbound

This paper cites Revisiting consensus error: A fine-grained analysis of local sgd under second-order data heterogeneity.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Revisiting consensus error: A fine-grained analysis of local sgd under second-order data heterogeneity

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:29.801382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe37dacc-1cc5-4c4b-9443-d2d9a4e3d7cd · outbound

This paper cites Federated learning: Collaborative machine learn- ing without centralized training data, Apr 2017.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Federated learning: Collaborative machine learn- ing without centralized training data, Apr 2017

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:29.911747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2148f948-01ab-44ea-bc42-d3748978e21f · outbound

This paper cites DiLoCo: Distributed Low-Communication Training of Language Models.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity DiLoCo: Distributed Low-Communication Training of Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.172502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207b0d2b-e4a1-48e8-a4aa-56a43eda292a · outbound

This paper cites Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.283353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f934804-aacf-4bde-965e-8c355ad5e9ac · outbound

This paper cites Communication-Efficient Learning of Deep Networks from Decentralized Data.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Communication-Efficient Learning of Deep Networks from Decentralized Data

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.427304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e4d267e-c7e5-4bae-9513-aab695b485fb · outbound

This paper cites Graph oracle models, lower bounds, and gaps for parallel stochastic optimization.Advances in neural information processing systems, 31, 2018.(Cited on pages 2 and 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Graph oracle models, lower bounds, and gaps for parallel stochastic optimization.Advances in neural information processing systems, 31, 2018.(Cited on pages 2 and 3)

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.554670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0344b03b-56c0-45ae-9f90-c0f295747a33 · outbound

This paper cites Advances and Open Problems in Federated Learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Advances and Open Problems in Federated Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.669742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e0a2dd5-aac2-4227-a3b7-2a8d284aa987 · outbound

This paper cites A Field Guide to Federated Optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity A Field Guide to Federated Optimization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.815693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b565ad-fe32-4295-abc8-50d32e290356 · outbound

This paper cites Scaffold: Stochastic controlled averaging for federated learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Scaffold: Stochastic controlled averaging for federated learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:30.935131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e33e83d-e2f1-4d37-a159-2cbcd2c7db36 · outbound

This paper cites A stochastic newton algorithm for distributed convex optimization.Advances in Neural Informa- tion Processing Systems, 34, 2021.(Cited on page 2).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity A stochastic newton algorithm for distributed convex optimization.Advances in Neural Informa- tion Processing Systems, 34, 2021.(Cited on page 2)

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.053408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25fcec20-b498-4928-aca8-c9d154b4fdc7 · outbound

This paper cites To- wards optimal communication complexity in distributed non-convex optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity To- wards optimal communication complexity in distributed non-convex optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.161062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b265dfbc-634f-4eb3-b339-625f06273690 · outbound

This paper cites Proxskip: Yes! local gradient steps provably lead to communication acceleration! finally! InInternational Conference on Machine Learning, pages 15750–15769.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Proxskip: Yes! local gradient steps provably lead to communication acceleration! finally! InInternational Conference on Machine Learning, pages 15750–15769

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.259764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8fc6ab5-0b26-402b-b370-e4e120330335 · outbound

This paper cites Fedsplit: An algorithmic framework for fast federated optimization.Advances in neural information processing systems, 33:7057–7066, 2020.(Cited on page 2) 59.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Fedsplit: An algorithmic framework for fast federated optimization.Advances in neural information processing systems, 33:7057–7066, 2020.(Cited on page 2) 59

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.347294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad2f54b-edcd-4f6a-aa87-2ac8eed99f70 · outbound

This paper cites Efficient large-scale distributed training of conditional maximum entropy models.Advances in neural information processing systems, 22, 2009.(Cited on pages 2 and 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Efficient large-scale distributed training of conditional maximum entropy models.Advances in neural information processing systems, 22, 2009.(Cited on pages 2 and 3)

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.425227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0756debe-2d47-40df-ad33-e0802b91ecdd · outbound

This paper cites Optimal distributed online prediction using mini-batches.Journal of Machine Learning Research, 13(1), 2012.(Cited on page 2).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Optimal distributed online prediction using mini-batches.Journal of Machine Learning Research, 13(1), 2012.(Cited on page 2)

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.527905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a06bcfd-7e34-4d99-91c8-3d5019906aef · outbound

This paper cites Local SGD Converges Fast and Communicates Little.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Local SGD Converges Fast and Communicates Little

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.636978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14996d1a-09e4-4e59-b2ee-ec1062246cec · outbound

This paper cites Is local sgd better than minibatch sgd? In International Conference on Machine Learning, pages 10334–10343.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Is local sgd better than minibatch sgd? In International Conference on Machine Learning, pages 10334–10343

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.745281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b4e8741-eae6-49d8-a965-23ec119f669b · outbound

This paper cites Communication-efficient distributed optimization using an approximate newton-type method.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Communication-efficient distributed optimization using an approximate newton-type method

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:31.916332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8557a0fb-60e2-476d-8e54-28046de04be3 · outbound

This paper cites Distributed optimization based on gradient tracking revisited: Enhancing convergence rate via surrogation.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Distributed optimization based on gradient tracking revisited: Enhancing convergence rate via surrogation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.049631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7d2cbdc-c4cf-4957-94a3-19bd0905c516 · outbound

This paper cites Optimal gradient sliding and its application to optimal distributed optimization under similarity.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Optimal gradient sliding and its application to optimal distributed optimization under similarity

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.195231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e4881f0-f920-4e79-adce-d56fb15177c2 · outbound

This paper cites Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.303301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3d5ac0-bf3d-4774-a6d2-2969b9a37b45 · outbound

This paper cites Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.455654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c5c9a13-a042-458c-a165-4de668db525d · outbound

This paper cites Federated optimization with doubly regularized drift correction.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Federated optimization with doubly regularized drift correction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.585018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 593f9e9e-abfb-4581-97bd-81e0f1364a00 · outbound

This paper cites Stabilized proximal-point methods for federated optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Stabilized proximal-point methods for federated optimization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.673629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e901d9c5-fe22-4e8b-8c52-c582257449ef · outbound

This paper cites The limits and potentials of local sgd for distributed heterogeneous learning with intermittent communication.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity The limits and potentials of local sgd for distributed heterogeneous learning with intermittent communication

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.768382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c69e06c-a653-44cb-9e62-babcaa48bc77 · outbound

This paper cites Parallelized stochastic gradient descent.Advances in neural information processing systems, 23, 2010.(Cited on page 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Parallelized stochastic gradient descent.Advances in neural information processing systems, 23, 2010.(Cited on page 3)

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:32.905043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc8deab-3d8a-4477-bba5-725b02071f76 · outbound

This paper cites Parallel SGD: When does averaging help?.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Parallel SGD: When does averaging help?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.058355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21721e3-94c2-4571-b6d4-8e85301388e5 · outbound

This paper cites Communication trade-offs for local-sgd with large step size.Advances in Neural Information Processing Systems, 32, 2019.(Cited on page 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Communication trade-offs for local-sgd with large step size.Advances in Neural Information Processing Systems, 32, 2019.(Cited on page 3)

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.183436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 981d2a50-16ff-4a7e-a6cf-8b828a669bec · outbound

This paper cites Tighter theory for local sgd on identical and heterogeneous data.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Tighter theory for local sgd on identical and heterogeneous data

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.297384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc461de2-3810-4784-b3fa-078a6f1f349f · outbound

This paper cites A unified theory of decentralized sgd with changing topology and local updates.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity A unified theory of decentralized sgd with changing topology and local updates

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.409165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec4b2f0b-f933-4668-84f7-f1fba4f2e131 · outbound

This paper cites an unresolved cited work.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.518436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee988099-68cd-4909-9d77-4d8bec448418 · outbound

This paper cites Federated accelerated stochastic gradient descent.Advances in Neural Information Processing Systems, 33:5332–5344, 2020.(Cited on page 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Federated accelerated stochastic gradient descent.Advances in Neural Information Processing Systems, 33:5332–5344, 2020.(Cited on page 3)

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.608093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 078753aa-ddef-4710-84b1-48f0416c7b6c · outbound

This paper cites The min-max complexity of distributed stochastic convex optimization with intermittent communication.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity The min-max complexity of distributed stochastic convex optimization with intermittent communication

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.764309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1045e958-2ddc-4e31-b309-b5cea591628d · outbound

This paper cites The Minimax Complexity of Distributed Optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity The Minimax Complexity of Distributed Optimization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:33.887318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 174e4db0-e822-4372-933b-cac6219dbe89 · outbound

This paper cites Sharp bounds for federated averaging (local sgd) and continuous perspective.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Sharp bounds for federated averaging (local sgd) and continuous perspective

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.003071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94606414-ef0b-4efa-a469-a8b6a066f6a1 · outbound

This paper cites On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.128102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf91b17-ae8f-405a-9d3a-9e686902fec1 · outbound

This paper cites Federated online and bandit convex optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Federated online and bandit convex optimization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.290366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf303262-c5b1-4468-865c-b258ff32112f · outbound

This paper cites On the still unreasonable effectiveness of federated averaging for heterogeneous distributed learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity On the still unreasonable effectiveness of federated averaging for heterogeneous distributed learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.412226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e61088c8-7efe-4cdf-b947-aaaca15d607b · outbound

This paper cites Refined analysis of constant step size federated averaging and federated richardson- romberg extrapolation.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Refined analysis of constant step size federated averaging and federated richardson- romberg extrapolation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.536439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec1363b4-437c-4472-83a7-f59a4de47b90 · outbound

This paper cites What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.666750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 580c4612-1c30-4bb8-bd24-dbeb03aa1177 · outbound

This paper cites Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.793452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d78ea2bf-f976-4365-8086-664496b4677d · outbound

This paper cites Understanding outer optimizers in local sgd: Learning rates, momentum, and acceleration.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Understanding outer optimizers in local sgd: Learning rates, momentum, and acceleration

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:34.902190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6811ed37-4c4c-4afc-a87e-a9ada013e3fe · outbound

This paper cites Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.023489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921a40a5-c45f-412b-be36-dcf97bb0c60b · outbound

This paper cites MuLoCo: Muon is a practical inner optimizer for DiLoCo.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity MuLoCo: Muon is a practical inner optimizer for DiLoCo

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.139882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be95cc7f-8847-40b2-a9c4-a108dad60c63 · outbound

This paper cites Sparsified sgd with memory.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Sparsified sgd with memory

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.251915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b4ff6c2-3fdb-4752-b842-a2c29a0cd660 · outbound

This paper cites Error feedback fixes signsgd and other gradient compression schemes.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Error feedback fixes signsgd and other gradient compression schemes

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.410514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691d8c5f-66d3-446e-b4b6-5555961b6e9a · outbound

This paper cites EControl: Fast distributed optimization with compression and error control.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity EControl: Fast distributed optimization with compression and error control

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.553559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dbcb4da-4a0d-4434-9921-f4044207936d · outbound

This paper cites Federated learning with partial model personalization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Federated learning with partial model personalization

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.689926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 393942da-e835-4fe6-aebd-28ab3573fe7a · outbound

This paper cites Partially personalized federated learning: Breaking the curse of data heterogeneity.Transactions on Machine Learning Research, 2025.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Partially personalized federated learning: Breaking the curse of data heterogeneity.Transactions on Machine Learning Research, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.878690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c82f1c9-7782-40ce-ba79-ce7255b56c2c · outbound

This paper cites The convergence of sparsified gradient methods.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity The convergence of sparsified gradient methods

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:35.979529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5879b3de-5128-4280-a70e-1ba2c87c49bb · outbound

This paper cites On maintaining linear con- vergence of distributed learning and optimization under limited communication.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity On maintaining linear con- vergence of distributed learning and optimization under limited communication

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.089958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47fd1cef-baf1-451c-a22e-8abaf26c5ea6 · outbound

This paper cites Communication-computation efficient gradient coding.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Communication-computation efficient gradient coding

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.189427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 236027ff-6a7b-45ec-975e-888553c6a9e0 · outbound

This paper cites The error-feedback framework: Better rates for sgd with delayed gradients and compressed updates.Journal of Machine Learning Research, 2020.(Cited on page 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity The error-feedback framework: Better rates for sgd with delayed gradients and compressed updates.Journal of Machine Learning Research, 2020.(Cited on page 3)

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.331291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62d35fd1-569c-4db5-81f2-8ba7722aae2b · outbound

This paper cites Asgrad: A sharp unified analysis of asynchronous-sgd algorithms.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Asgrad: A sharp unified analysis of asynchronous-sgd algorithms

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.453567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb5423e-55fd-44c7-a728-b1ffef3404e3 · outbound

This paper cites Federated learning with differential privacy: Algorithms and performance analysis.IEEE transactions on information forensics and security, 15:3454–3469, 2020.(Cited on page 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Federated learning with differential privacy: Algorithms and performance analysis.IEEE transactions on information forensics and security, 15:3454–3469, 2020.(Cited on page 3)

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.502435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dfd85cd-3956-4288-a460-65c2e2d79b52 · outbound

This paper cites Shuffled model of differential privacy in federated learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Shuffled model of differential privacy in federated learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.562785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0e10e10-6a80-4a6b-b4cb-8eae72300761 · outbound

This paper cites Private non-convex federated learning without a trusted server.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Private non-convex federated learning without a trusted server

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.703911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 129b7927-40d8-4a85-a41b-78fe2a9efe82 · outbound

This paper cites Diff2: Differential private optimization via gradient differ- ences for nonconvex distributed learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Diff2: Differential private optimization via gradient differ- ences for nonconvex distributed learning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.864249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b19f9dd-1792-425a-8c37-462286ff828e · outbound

This paper cites Efficient private federated non-convex optimization with shuffled model.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Efficient private federated non-convex optimization with shuffled model

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.936692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5b17f8e-762c-4ae2-8128-1a30c17cb166 · outbound

This paper cites Double momentum and error feedback for clipping with fast rates and differential privacy.arXiv preprint arXiv:2502.11682, 2025.(Cited on page 3) 62.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Double momentum and error feedback for clipping with fast rates and differential privacy.arXiv preprint arXiv:2502.11682, 2025.(Cited on page 3) 62

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:36.996395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b46527ca-41a9-4d39-8be8-2e9dd294e0b9 · outbound

This paper cites Smoothed Normalization for Efficient Distributed Private Optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Smoothed Normalization for Efficient Distributed Private Optimization

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.113173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ade7067-c53e-4fec-bdac-84ae4241bb1f · outbound

This paper cites Byzantine stochastic gradient descent.Advances in neural information processing systems, 31, 2018.(Cited on page 3).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Byzantine stochastic gradient descent.Advances in neural information processing systems, 31, 2018.(Cited on page 3)

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.207654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e03a5f9e-2c6d-420c-8295-bee7f8012e39 · outbound

This paper cites Learning from history for byzantine robust optimization.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Learning from history for byzantine robust optimization

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.249182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82c03000-1081-49f1-958b-5f24e42a8649 · outbound

This paper cites Byzantine-robust and differentially private federated optimization under weaker assumptions.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Byzantine-robust and differentially private federated optimization under weaker assumptions

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.326765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b561a93c-3057-4cf1-a937-6c61e1e04077 · outbound

This paper cites On the Outsized Importance of Learning Rates in Local Update Methods.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity On the Outsized Importance of Learning Rates in Local Update Methods

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.433836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2dfdf7c-993d-4feb-9638-8a239feb9719 · outbound

This paper cites Don't Use Large Mini-Batches, Use Local SGD.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Don't Use Large Mini-Batches, Use Local SGD

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.539772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d80bc5a-f943-4357-8b2b-f078ca758424 · outbound

This paper cites Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.653772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a12d866-3385-412c-a97a-027761c28e97 · outbound

This paper cites Collaborative pac learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Collaborative pac learning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.767708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1eee434-dff8-41e9-aeb3-415144cee9d1 · outbound

This paper cites On the Effect of Defections in Federated Learning and How to Prevent Them.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity On the Effect of Defections in Federated Learning and How to Prevent Them

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:37.851410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c539fe00-4a7c-441c-9992-d8e19325b983 · outbound

This paper cites FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:38.000279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1d70dc-5aae-43d4-b7c7-bd2c59aaefd1 · outbound

This paper cites Quelques propriétés des opérateurs angle-bornés et n-cycliquement monotones.Israel Journal of Mathematics, 26(2):137–150, 1977.(Cited on page 19).

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity Quelques propriétés des opérateurs angle-bornés et n-cycliquement monotones.Israel Journal of Mathematics, 26(2):137–150, 1977.(Cited on page 19)

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:38.120742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ab9637-fda4-4941-823d-fa4eef0d28cc · outbound

This paper cites The Baillon-Haddad Theorem Revisited.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity The Baillon-Haddad Theorem Revisited

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T01:23:38.229914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers