Minimax squared l2 error for robust mean estimation under star-shaped sets with heavy-tailed noise and contamination level ε is max(δ*², ε σ²) ∧ d², where δ* is the largest scale satisfying N δ²/σ² ≤ log M^loc(δ, c).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust mean estimation under star-shaped constraints with heavy-tailed noise
Minimax squared l2 error for robust mean estimation under star-shaped sets with heavy-tailed noise and contamination level ε is max(δ*², ε σ²) ∧ d², where δ* is the largest scale satisfying N δ²/σ² ≤ log M^loc(δ, c).