74 citations
- Saarland UniversityDE15 papers
- Ruhr University BochumDE11 papers
- Max Planck Institute for InformaticsDE8 papers
- Max Planck Institute for Security and PrivacyDE7 papers
- Leibniz University HannoverDE6 papers
- Technical University of MunichDE5 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- KU LeuvenBE4 papers
- Purdue University West LafayetteUS4 papers
- Technische Universität BerlinDE4 papers
- Arizona State UniversityUS3 papers
- École Polytechnique Fédérale de LausanneCH3 papers
Showing 2023 · cs.LGShow all
2 papers · 2 filters
cs.LG2023★ 4 cited
Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
Bo Li, Yasin Esfandiari, Mikkel N. Schmidt +2
In federated learning, data heterogeneity is a critical challenge. A straightforward solution is to shuffle the clients' data to homogenize the distribution. However, this may viol…
cs.LG2023★ 4 cited
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
Anastasia Koloskova, Hadrien Hendrikx, Sebastian U. Stich
Gradient clipping is a popular modification to standard (stochastic) gradient descent, at every iteration limiting the gradient norm to a certain value . It is widely used fo…