A variable smoothing method for DC composite optimization is proposed for robust phase retrieval, with convergence to DC critical points and experiments indicating better outlier robustness than ℓ1 loss.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
math.OC 3verdicts
UNVERDICTED 3representative citing papers
Entropy-regularized stochastic games are defined with proofs of value existence for N-stage and discounted cases, sufficiency of Markovian and stationary strategies, and convex optimization algorithms for computation.
A joint spectral-radius technique for the product of two ADMM matrices tightens local linear convergence bounds compared with separate norm products.
citing papers explorer
-
A DC Composite Optimization via Variable Smoothing for Robust Phase Retrieval with Nonconvex Loss Functions
A variable smoothing method for DC composite optimization is proposed for robust phase retrieval, with convergence to DC critical points and experiments indicating better outlier robustness than ℓ1 loss.
-
Entropy-Regularized Stochastic Games
Entropy-regularized stochastic games are defined with proofs of value existence for N-stage and discounted cases, sufficiency of Markovian and stationary strategies, and convex optimization algorithms for computation.
-
New results on the local linear convergence of ADMM: a joint approach
A joint spectral-radius technique for the product of two ADMM matrices tightens local linear convergence bounds compared with separate norm products.