Establishes exponential convergence in Wasserstein distance for the mean-field limit and finite-particle approximation of a consensus-based method solving nonconvex bi-level optimization problems.
Global minima of overparameterized neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Overparameterization adds symmetries that precondition the Hessian for better minima and increase the probability mass of global minima near typical initializations.
citing papers explorer
-
Convergence of Consensus-Based Particle Methods for Nonconvex Bi-Level Optimization
Establishes exponential convergence in Wasserstein distance for the mean-field limit and finite-particle approximation of a consensus-based method solving nonconvex bi-level optimization problems.
-
The Role of Symmetry in Optimizing Overparameterized Networks
Overparameterization adds symmetries that precondition the Hessian for better minima and increase the probability mass of global minima near typical initializations.