Develops an adaptive proximal ADMM that achieves state-of-the-art iteration complexity for approximate first-order stationary points in nonconvex composite problems with linear constraints, without rank assumptions and allowing inexact subproblem solves.
Statistical consistency and asymptotic normality for high-dimensional robustM-estimators,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
DPD-Lasso integrates density power divergence and Lasso regularization into an iterative algorithm for stable regression on clean and contaminated data from MII aerosol jet printing experiments.
citing papers explorer
-
An Adaptive Proximal ADMM for Nonconvex Linearly Constrained Composite Programs
Develops an adaptive proximal ADMM that achieves state-of-the-art iteration complexity for approximate first-order stationary points in nonconvex composite problems with linear constraints, without rank assumptions and allowing inexact subproblem solves.
-
Robust Analysis for Resilient AI System
DPD-Lasso integrates density power divergence and Lasso regularization into an iterative algorithm for stable regression on clean and contaminated data from MII aerosol jet printing experiments.