A certificate-based regret analysis framework for guided-diffusion black-box optimization is introduced, with mass lift as the central quantity explaining convergence from pretrained generators.
arXiv preprint arXiv:2403.13219 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 8representative citing papers
Conditional diffusion models trained with BO-aware strategies approximate the optimum distribution, enabling a Diffusion-based Mode Seeking acquisition function with a sub-optimality guarantee that outperforms baselines in experiments.
PGM framework links diffusion to proximal regularization for closed-form Moreau-score sampling in Bayesian inverse problems, learned only from prior samples.
GeoCoupling optimizes temporal couplings between modalities in biomolecular generative models and outperforms synchronous baselines on drug design and protein design tasks.
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
A new error-damping estimator for compositional score matching enables stable amortized inference on hierarchical Bayesian models with over 750,000 parameters using fewer than one full model simulation on large problems.
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.
citing papers explorer
-
Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs
A certificate-based regret analysis framework for guided-diffusion black-box optimization is introduced, with mass lift as the central quantity explaining convergence from pretrained generators.
-
Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models
Conditional diffusion models trained with BO-aware strategies approximate the optimum distribution, enabling a Diffusion-based Mode Seeking acquisition function with a sub-optimality guarantee that outperforms baselines in experiments.
-
Proximal-Based Generative Modeling for Bayesian Inverse Problems
PGM framework links diffusion to proximal regularization for closed-form Moreau-score sampling in Bayesian inverse problems, learned only from prior samples.
-
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
GeoCoupling optimizes temporal couplings between modalities in biomolecular generative models and outperforms synchronous baselines on drug design and protein design tasks.
-
GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
-
Compositional amortized inference for large-scale hierarchical Bayesian models
A new error-damping estimator for compositional score matching enables stable amortized inference on hierarchical Bayesian models with over 750,000 parameters using fewer than one full model simulation on large problems.
-
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
-
On the Robustness of Distribution Support under Diffusion Guidance
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.