REVIEW 6 cited by
Diffusion Model for Data-Driven Black-Box Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Generative AI has redefined artificial intelligence, enabling the creation of innovative content and customized solutions that drive business practices into a new era of efficiency and creativity. In this paper, we focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization over complex structured variables. Consider the practical scenario where one wants to optimize some structured design in a high-dimensional space, based on massive unlabeled data (representing design variables) and a small labeled dataset. We study two practical types of labels: 1) noisy measurements of a real-valued reward function and 2) human preference based on pairwise comparisons. The goal is to generate new designs that are near-optimal and preserve the designed latent structures. Our proposed method reformulates the design optimization problem into a conditional sampling problem, which allows us to leverage the power of diffusion models for modeling complex distributions. In particular, we propose a reward-directed conditional diffusion model, to be trained on the mixed data, for sampling a near-optimal solution conditioned on high predicted rewards. Theoretically, we establish sub-optimality error bounds for the generated designs. The sub-optimality gap nearly matches the optimal guarantee in off-policy bandits, demonstrating the efficiency of reward-directed diffusion models for black-box optimization. Moreover, when the data admits a low-dimensional latent subspace structure, our model efficiently generates high-fidelity designs that closely respect the latent structure. We provide empirical experiments validating our model in decision-making and content-creation tasks.
Forward citations
Cited by 6 Pith papers
-
Provable Maximum Entropy Manifold Exploration via Diffusion Models
S-MEME iteratively fine-tunes a diffusion model using its own score as the exploration reward, provably converging to the maximum-entropy distribution on the learned manifold.
-
Adjoint-Based Aerodynamic Shape Optimization with a Manifold Constraint Learned by Diffusion Models
Airfoil drag minimization is reformulated as optimization in the latent space of a diffusion model, with CFD adjoint gradients backpropagated through the diffusion sampler; the approach beats a Hicks-Henne baseline in...
-
ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
A two-step wrapper (invert candidate to latent, then run DPS from that latent) improves hard inpainting results, with mixed or negative superresolution results and toy-model theory.
-
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
A SVD-based, coordinate-wise DDIM sampler is claimed to asymptotically sample from the posterior for noisy linear inverse problems, but the proof's posterior identification step does not follow from the stated updates.
-
A Reward-Directed Diffusion Framework for Generative Design Optimization
The paper reports a reward-directed diffusion framework that fine-tunes a DDPM with reward-weighted likelihood and then samples with soft-value importance weighting, claiming 25% resistance reduction in ship hulls and...
-
Optimal Reward Shaping: Autonomous Car Parking Case Study
Co-optimizing a parameterized parking reward with DQN hyperparameters via Bayesian search raises mean parking score from ~27 to 95.6 and removes paralysis and over-caution failure modes.
Discussion (0). Continue with ORCID to comment.