Proposes a covariance-aware tuning-free shrinkage framework and sequential algorithm for multi-source estimation that attains oracle risk asymptotically and improves on single-step methods.
Robust fed- erated learning in a heterogeneous environment
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
Establishes tight finite-time convergence rates for online distributed linear estimation under adversarial measurements and asynchrony via a two-timescale l1-minimization algorithm, plus relaxed matrix conditions for projected recovery.
FedBiCross adds client clustering, adaptive cross-cluster weighting, and local fine-tuning to data-free one-shot federated learning, reporting large accuracy jumps on four medical image datasets.
BoBa uses data distribution inference and overlapping clustering with voting to detect backdoor attacks in non-IID federated learning, claiming attack success rates below 0.001.
citing papers explorer
-
Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage
Proposes a covariance-aware tuning-free shrinkage framework and sequential algorithm for multi-source estimation that attains oracle risk asymptotically and improves on single-step methods.
-
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
FAR-SIGN achieves adversary-resilient fully asynchronous optimization via signed directional projections and two-timescale correction, with almost-sure convergence to stationary points at rates O(n^{-1/4+ε}) first-order and O(n^{-1/6+ε}) zeroth-order.
-
Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements
Establishes tight finite-time convergence rates for online distributed linear estimation under adversarial measurements and asynchrony via a two-timescale l1-minimization algorithm, plus relaxed matrix conditions for projected recovery.
-
FedBiCross: Personalized One-Shot Federated Learning on Medical Images
FedBiCross adds client clustering, adaptive cross-cluster weighting, and local fine-tuning to data-free one-shot federated learning, reporting large accuracy jumps on four medical image datasets.
-
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
BoBa uses data distribution inference and overlapping clustering with voting to detect backdoor attacks in non-IID federated learning, claiming attack success rates below 0.001.