Skip to main content
Ryan Orban

Ryan Orban

Subject
4 entries

Federated Learning

Bookmarks

  1. Secure Byzantine-Robust Machine Learning

    He, Karimireddy, and Jaggi propose a two-server cryptographic protocol that simultaneously achieves Byzantine robustness, input privacy, and local differential privacy for distributed machine learning — three properties usually addressed separately. Bridges the privacy-robustness gap in federated learning.

  2. Learning from History for Byzantine Robust Optimization

    Karimireddy, He, and Jaggi (EPFL, arXiv:2012.10333, 2021) propose using historical gradient information to detect and filter Byzantine workers in distributed training, achieving near-optimal convergence even with a constant fraction of corrupt workers. The historical approach is notable because it breaks the fundamental limitation of single-round Byzantine filters without requiring cryptographic overhead.

  3. DISCO: Decentralized Privacy-Preserving ML Training

    DISCO (from EPFL) is a decentralized, privacy-preserving ML training framework using peer-to-peer networking — no central server, nodes train locally and share model updates directly. Extends federated learning to remove the trusted aggregator requirement.

  4. Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing

    EPFL researchers show that existing Byzantine-robust aggregation rules (Krum, coordinate-wise median, RFA) fail catastrophically on non-iid data, then fix the problem with a one-step bucketing scheme that randomly groups worker updates before aggregation. The first result with provable convergence guarantees for Byzantine robustness under realistic data heterogeneity.

All bookmarks