Pith. sign in

Lower Bound for Randomized First Order Convex Optimization

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We provide an explicit construction and direct proof for the lower bound on the number of first order oracle accesses required for a randomized algorithm to minimize a convex Lipschitz function.

fields

math.OC 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

The Adaptive Complexity of Finding a Stationary Point

math.OC · 2025-05-14 · conditional · novelty 7.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Adaptive Complexity of Finding a Stationary Point math.OC · 2025-05-14 · conditional · none · ref 50 · internal anchor

    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.