A distributed framework with trace-similarity penalty and invex relaxation achieves two-phase minimax optimal rates and sharper model-free prediction error bounds under unidentifiable parameters and heterogeneity.
Towards Personalized Federated Learning , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Distributed Prediction under Heterogeneity with Unidentifiable Parameter
A distributed framework with trace-similarity penalty and invex relaxation achieves two-phase minimax optimal rates and sharper model-free prediction error bounds under unidentifiable parameters and heterogeneity.
- Benchmark Evaluation of Federated Learning on Multi-organ Images