Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
Jiang, Samuel Daulton, Benjamin Letham, Andrew Gordon Wilson, and Eytan Bakshy
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 2
background 1
citation-polarity summary
verdicts
UNVERDICTED 7representative citing papers
MAESTRO couples surrogate optimization transport modeling with external solvers to enable efficient full-physics steady-state plasma predictions in fusion devices.
LILO integrates LLMs to translate natural language feedback into preference signals for Gaussian process-based Bayesian optimization, outperforming standard preference BO and LLM-only methods on benchmarks.
NEON provides uncertainty-aware operator learning for composite Bayesian optimization in function spaces using a single network, achieving claimed SOTA with orders of magnitude fewer parameters than ensembles.
A trust-region Bayesian optimization framework integrates LEED multiple scattering models to jointly optimize structural and experimental parameters for automated surface reconstruction.
spotoptim is an open-source Python package that implements a Kriging-based optimization loop with Expected Improvement, mixed-variable support, noise handling via OCBA, parallelization, and restart mechanisms for black-box optimization.
FMQA uses factorization machines as surrogates for black-box optimization, converting them directly into QUBO problems solvable by Ising machines for faster acquisition function optimization.
citing papers explorer
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
Accelerating integrated modeling with surrogate-based optimization: the MAESTRO workflow
MAESTRO couples surrogate optimization transport modeling with external solvers to enable efficient full-physics steady-state plasma predictions in fusion devices.
-
LILO: Bayesian Optimization with Natural Language Feedback
LILO integrates LLMs to translate natural language feedback into preference signals for Gaussian process-based Bayesian optimization, outperforming standard preference BO and LLM-only methods on benchmarks.
-
Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks
NEON provides uncertainty-aware operator learning for composite Bayesian optimization in function spaces using a single network, achieving claimed SOTA with orders of magnitude fewer parameters than ensembles.
-
Physics-informed automated surface reconstructing via low-energy electron diffraction based on Bayesian optimization
A trust-region Bayesian optimization framework integrates LEED multiple scattering models to jointly optimize structural and experimental parameters for automated surface reconstruction.
-
Optimization with SpotOptim
spotoptim is an open-source Python package that implements a Kriging-based optimization loop with Expected Improvement, mixed-variable support, noise handling via OCBA, parallelization, and restart mechanisms for black-box optimization.
-
Black-box optimization using factorization and Ising machines
FMQA uses factorization machines as surrogates for black-box optimization, converting them directly into QUBO problems solvable by Ising machines for faster acquisition function optimization.