Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Huang, Xinmeng"'
Large and complex datasets are often collected from several, possibly heterogeneous sources. Collaborative learning methods improve efficiency by leveraging commonalities across datasets while accounting for possible differences among them. Here we s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56190dd2d1ff93bf52fcf6fd10a895f5
http://arxiv.org/abs/2306.06291
http://arxiv.org/abs/2306.06291
Communication compression is a common technique in distributed optimization that can alleviate communication overhead by transmitting compressed gradients and model parameters. However, compression can introduce information distortion, which slows do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9f027b51e0b7e41c4077c71330e3902
http://arxiv.org/abs/2305.16297
http://arxiv.org/abs/2305.16297
Communication compression is an essential strategy for alleviating communication overhead by reducing the volume of information exchanged between computing nodes in large-scale distributed stochastic optimization. Although numerous algorithms with co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d8cb4b41cb2ea0f694e4c8da1e1d6df
Federated learning is a powerful paradigm for large-scale machine learning, but it faces significant challenges due to unreliable network connections, slow communication, and substantial data heterogeneity across clients. FedAvg and SCAFFOLD are two
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::529943378e8d801152a099117cc778f5
Evaluating the performance of machine learning models under distribution shift is challenging, especially when we only have unlabeled data from the shifted (target) domain, along with labeled data from the original (source) domain. Recent work sugges
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4495f58cc21be6665a3b887da5b1fb28
Autor:
Huang, Xinmeng, Yuan, Kun
Decentralized optimization with time-varying networks is an emerging paradigm in machine learning. It saves remarkable communication overhead in large-scale deep training and is more robust in wireless scenarios especially when nodes are moving. Fede
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4b8002cb17e37dda12d20d1cc986c378
http://arxiv.org/abs/2211.00533
http://arxiv.org/abs/2211.00533
Recent advances in distributed optimization and learning have shown that communication compression is one of the most effective means of reducing communication. While there have been many results on convergence rates under communication compression,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e670882db4f21ceb620dd6a9bccae10
The prediction accuracy of machine learning methods is steadily increasing, but the calibration of their uncertainty predictions poses a significant challenge. Numerous works focus on obtaining well-calibrated predictive models, but less is known abo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53df87f27fa59d7712878baff6dd6fa5
In modern machine learning, users often have to collaborate to learn the distribution of the data. Communication can be a significant bottleneck. Prior work has studied homogeneous users -- i.e., whose data follow the same discrete distribution -- an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e572e48dfcf9ff4a603394fc172d19c
Decentralized optimization is effective to save communication in large-scale machine learning. Although numerous algorithms have been proposed with theoretical guarantees and empirical successes, the performance limits in decentralized optimization,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::510f8630edfd2e96641c2d0974eace08