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.
Global Strategy Journal , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative 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.