The adaptive round complexity of finding an epsilon-stationary point is Omega(epsilon^{-(p+1)/p}) in high dimension even with poly(d) parallel queries, and near-matching per-round query bounds are given in constant dimension.
The adaptive complexity of maximizing a submodular function
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Adaptive Complexity of Finding a Stationary Point
The adaptive round complexity of finding an epsilon-stationary point is Omega(epsilon^{-(p+1)/p}) in high dimension even with poly(d) parallel queries, and near-matching per-round query bounds are given in constant dimension.