Machine learningMachine learning

Regularizēta federatīvā apmācība

Regularizēta federatīvā apmācība paplašina federatīvās apmācības sistēmu, pievienojot soda locekļus katra klienta lokālajam mērķim, turot lokālās atjauninājumus tuvāk globālajam modelim. Kanoniskā formulācija — FedProx — pievieno proksimālu locekli, kas kontrolē, cik tālu var novirzities atsevišķs klients, uzlabojot konverģenci un stabilitāti, ja klientu datu sadalījumi būtiski atšķiras.

Atvērt MethodMindDrīzumāVideoDrīzumāDownload slides

Lasīt pilno metodes aprakstu

Tikai dalībniekiem

Piesakieties ar bezmaksas kontu, lai lasītu šo sadaļu.

Pieteikties

Method map

The neighbourhood of related methods — select a node to explore.

Avoti

  1. Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated Optimization in Heterogeneous Networks. Proceedings of Machine Learning and Systems (MLSys), 2, 429–450. link
  2. McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 54, 1273–1282. link

Kā citēt šo lapu

ScholarGate. (2026, June 3). Regularized Federated Learning (Proximal and Penalty-Based Approaches). ScholarGate. https://scholargate.app/lv/machine-learning/regularized-federated-learning

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side
ScholarGateRegularized Federated Learning (Regularized Federated Learning (Proximal and Penalty-Based Approaches)). Izgūts 2026-06-15 no https://scholargate.app/lv/machine-learning/regularized-federated-learning · Datu kopa: https://doi.org/10.5281/zenodo.20539026