The GMUDC framework provides topology-aware upper and lower bounds on reconstruction risk for nonlinear functions in RKHS under per-server computation and communication budgets in both quenched and annealed regimes.
Distributed ridge regression: optimal rates and communication trade-offs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
General Multi-User Distributed Computing: A Learning-Theoretic RKHS Framework for Generic Nonlinear Target Functions with Topology-Aware Risk Analysis
The GMUDC framework provides topology-aware upper and lower bounds on reconstruction risk for nonlinear functions in RKHS under per-server computation and communication budgets in both quenched and annealed regimes.