For φ-divergences with superlinear growth, sample average approximation achieves P-independent sample complexity for worst-case expectation estimation depending only on φ's growth, ball radius and precision, with optimality via lower bounds; non-superlinear φ yields unbounded P-dependent complexity.
Improved sample complexity bounds for distribution- ally robust reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sample Average Approximation for Distributionally Robust Optimization with $\phi$-divergences
For φ-divergences with superlinear growth, sample average approximation achieves P-independent sample complexity for worst-case expectation estimation depending only on φ's growth, ball radius and precision, with optimality via lower bounds; non-superlinear φ yields unbounded P-dependent complexity.