Unifies ES, CBO, and OVI black-box optimizers via two design axes and proposes hybrid methods that outperform base algorithms on benchmarks.
Gradient is All You Need ?, 2023
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Truncating noise in CBO bounds higher moments of the particle law and enables a rigorous proof of convergence in expectation to the global minimizer via Wasserstein-2 distance analysis under minimal assumptions.
citing papers explorer
-
Bridging Spherical Black-Box Optimizers
Unifies ES, CBO, and OVI black-box optimizers via two design axes and proposes hybrid methods that outperform base algorithms on benchmarks.
-
Consensus-Based Optimization with Truncated Noise
Truncating noise in CBO bounds higher moments of the particle law and enables a rigorous proof of convergence in expectation to the global minimizer via Wasserstein-2 distance analysis under minimal assumptions.