A unified recursion framework for stochastic variance-reduced estimation yields high-probability bounds and the first Õ(ε^{-3}) oracle complexity for stochastic optimization with expectation constraints.
Efficiency of minimizing compositions of convex functions and smooth maps.Mathematical Programming, 178(1):503–558
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
SURF derives weight sampling rules from the arc-length CDF of the scalarization path to uniformly traverse the Pareto front in multi-objective optimization.
AGILS is an alternating gradient algorithm for bilevel optimization that uses Moreau envelope reformulation to handle inexact lower-level solves, with convergence to stationary points proven under stated assumptions.
citing papers explorer
-
Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
A unified recursion framework for stochastic variance-reduced estimation yields high-probability bounds and the first Õ(ε^{-3}) oracle complexity for stochastic optimization with expectation constraints.
-
SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
SURF derives weight sampling rules from the arc-length CDF of the scalarization path to uniformly traverse the Pareto front in multi-objective optimization.
-
Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation
AGILS is an alternating gradient algorithm for bilevel optimization that uses Moreau envelope reformulation to handle inexact lower-level solves, with convergence to stationary points proven under stated assumptions.