Zobrazeno 1 - 10
of 101
pro vyhledávání: '"He, Lie"'
Collaborative learning is an important tool to train multiple clients more effectively by enabling communication among clients. Identifying helpful clients, however, presents challenging and often introduces significant overhead. In this paper, we mo
Externí odkaz:
http://arxiv.org/abs/2409.05539
Identifying clients with similar objectives and learning a model-per-cluster is an intuitive and interpretable approach to personalization in federated learning. However, doing so with provable and optimal guarantees has remained an open challenge. W
Externí odkaz:
http://arxiv.org/abs/2306.08393
Autor:
He, Lie, Kasiviswanathan, Shiva Prasad
In this paper, we study the conditional stochastic optimization (CSO) problem which covers a variety of applications including portfolio selection, reinforcement learning, robust learning, causal inference, etc. The sample-averaged gradient of the CS
Externí odkaz:
http://arxiv.org/abs/2304.10613
In this paper, we study the challenging task of Byzantine-robust decentralized training on arbitrary communication graphs. Unlike federated learning where workers communicate through a server, workers in the decentralized environment can only talk to
Externí odkaz:
http://arxiv.org/abs/2202.01545
Autor:
Vogels, Thijs, He, Lie, Koloskova, Anastasia, Lin, Tao, Karimireddy, Sai Praneeth, Stich, Sebastian U., Jaggi, Martin
Publikováno v:
Advances in Neural Information Processing Systems 34, 2021
In decentralized machine learning, workers compute model updates on their local data. Because the workers only communicate with few neighbors without central coordination, these updates propagate progressively over the network. This paradigm enables
Externí odkaz:
http://arxiv.org/abs/2110.04175
Publikováno v:
In Nuclear and Particle Physics Proceedings June 2024 344:31-38
Byzantine robustness has received significant attention recently given its importance for distributed and federated learning. In spite of this, we identify severe flaws in existing algorithms even when the data across the participants is identically
Externí odkaz:
http://arxiv.org/abs/2012.10333
In Byzantine robust distributed or federated learning, a central server wants to train a machine learning model over data distributed across multiple workers. However, a fraction of these workers may deviate from the prescribed algorithm and send arb
Externí odkaz:
http://arxiv.org/abs/2006.09365
Increasingly machine learning systems are being deployed to edge servers and devices (e.g. mobile phones) and trained in a collaborative manner. Such distributed/federated/decentralized training raises a number of concerns about the robustness, priva
Externí odkaz:
http://arxiv.org/abs/2006.04747
Autor:
Kairouz, Peter, McMahan, H. Brendan, Avent, Brendan, Bellet, Aurélien, Bennis, Mehdi, Bhagoji, Arjun Nitin, Bonawitz, Kallista, Charles, Zachary, Cormode, Graham, Cummings, Rachel, D'Oliveira, Rafael G. L., Eichner, Hubert, Rouayheb, Salim El, Evans, David, Gardner, Josh, Garrett, Zachary, Gascón, Adrià, Ghazi, Badih, Gibbons, Phillip B., Gruteser, Marco, Harchaoui, Zaid, He, Chaoyang, He, Lie, Huo, Zhouyuan, Hutchinson, Ben, Hsu, Justin, Jaggi, Martin, Javidi, Tara, Joshi, Gauri, Khodak, Mikhail, Konečný, Jakub, Korolova, Aleksandra, Koushanfar, Farinaz, Koyejo, Sanmi, Lepoint, Tancrède, Liu, Yang, Mittal, Prateek, Mohri, Mehryar, Nock, Richard, Özgür, Ayfer, Pagh, Rasmus, Raykova, Mariana, Qi, Hang, Ramage, Daniel, Raskar, Ramesh, Song, Dawn, Song, Weikang, Stich, Sebastian U., Sun, Ziteng, Suresh, Ananda Theertha, Tramèr, Florian, Vepakomma, Praneeth, Wang, Jianyu, Xiong, Li, Xu, Zheng, Yang, Qiang, Yu, Felix X., Yu, Han, Zhao, Sen
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data d
Externí odkaz:
http://arxiv.org/abs/1912.04977