Prox-ITEM achieves the minimax-optimal distance-to-solution rate among span-based first-order methods for smooth strongly convex composite problems, with Prox-TMM as its stationary limit matching TMM rates.
hub
Title resolution pending
3 Pith papers cite this work, alongside 5,811 external citations. Polarity classification is still indexing.
3
Pith papers citing it
5,811
external citations · OpenAlex
hub tools
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Develops two-level convergence theory for LS-AMG-DD showing coarse-space weak approximation property bounded by spectral cutoff threshold, yielding factored bounds for multiplicative cycles with block-Jacobi and overlapping Schwarz smoothers on Gram-representable SPD matrices.
Introduces and analyzes the λ-target update for linear Q-learning via geometric averaging of periodic target maps, studied with a switching-system model in the deterministic case.
citing papers explorer
-
An optimal first-order method for smooth and strongly convex composite optimization and its stationary limit
Prox-ITEM achieves the minimax-optimal distance-to-solution rate among span-based first-order methods for smooth strongly convex composite problems, with Prox-TMM as its stationary limit matching TMM rates.
-
Two-level convergence of Algebraic Multigrid with Overlapping Smoothers and Spectral Coarse Grids
Develops two-level convergence theory for LS-AMG-DD showing coarse-space weak approximation property bounded by spectral cutoff threshold, yielding factored bounds for multiplicative cycles with block-Jacobi and overlapping Schwarz smoothers on Gram-representable SPD matrices.
-
Geometrically Averaged Hard Target Updates for Linear Q-Learning
Introduces and analyzes the λ-target update for linear Q-learning via geometric averaging of periodic target maps, studied with a switching-system model in the deterministic case.