← Back to all news
arXiv Machine Learning By Yilin Zheng, Haowei Wang, Szu Hui Ng, Enlu Zhou

Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models

Read the original on arXiv Machine Learning →

arXiv:2606. 08438v1 Announce Type: cross Abstract: Bayesian optimization (BO) is a widely used approach for black-box optimization that uses a Gaussian process (GP) as a surrogate and guides sequential evaluations via an acquisition function, with the ultimate goal of locating the global optimum $\mathbf{x}^{\star}$.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 8

$\alpha$-PFN: Fast Entropy Search via In-Context Learning

arXiv:2606. 07134v1 Announce Type: new Abstract: Information-theoretic acquisition functions such as Entropy Search (ES) offer a principled exploration-exploitation framework for Bayesian optimization (BO).

By Herilalaina Rakotoarison, Steven Adriaensen, Tom Viering, Carl Hvarfner, Samuel M\"uller, Frank Hutter, Eytan Bakshy
llmsbenchmarks
More like this →
arXiv Machine Learning
Aug 31

Improved off-policy training of diffusion samplers

The paper investigates training diffusion models to sample from distributions defined by unnormalized densities or energy functions. It benchmarks various diffusion-structured inference techniques, including simulation-based variational methods and off-policy approaches such as continuous generative flow networks, highlighting their relative strengths and challenging some prior claims. Additionally, the authors introduce a new exploration strategy for off-policy methods that employs local search in the target space with a replay buffer, demonstrating improved sample quality across multiple target distributions.

By Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Esmeralda S. Whitammer
diffusionbenchmarks
More like this →
arXiv Machine Learning
Jun 2

Local Preferential Bayesian Optimization

arXiv:2606. 02351v1 Announce Type: new Abstract: Bayesian optimization (BO) is a popular and effective approach for tuning expensive, noisy experiments, but requires the formulation of an explicit objective function.

By Johanna Menn, Miriam Kober, Paul Brunzema, David Stenger, Sebastian Trimpe
benchmarks
More like this →