REVIEW 4 cited by
High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
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
read the original abstract
We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces. By adapting ideas from deep metric learning, we use label guidance from the blackbox function to structure the VAE latent space, facilitating the Gaussian process fit and yielding improved BO performance. Importantly for BO problem settings, our method operates in semi-supervised regimes where only few labelled data points are available. We run experiments on three real-world tasks, achieving state-of-the-art results on the penalised logP molecule generation benchmark using just 3% of the labelled data required by previous approaches. As a theoretical contribution, we present a proof of vanishing regret for VAE BO.
Forward citations
Cited by 4 Pith papers
-
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces
A decoupled Bayesian optimization method that samples candidate molecules from a VAE prior weighted by a structure-space Gaussian process's probability of improvement outperforms latent-space BO on low-budget molecula...
-
Optimization of time-consuming experimental conditions using pseudo-experimental data guided by adaptive polynomial regression
PolyBO fits a polynomial to the observed experimental data, labels random search-space points with its predictions, and adds them to the Bayesian-optimization surrogate, cutting iterations to a target regret on high-d...
-
Natural Evolutionary Search meets Probabilistic Numerics
The authors derive closed-form Bayesian-quadrature updates for CMA-ES, XNES, and SNES, yielding a family of sample-efficient probabilistic evolutionary strategies.
-
Learned Offline Query Planning via Bayesian Optimization
BayesQO combines variational autoencoders and Bayesian optimization with censored timeouts to discover faster join-order plans offline for repetitive analytic workloads.
Discussion (0). Continue with ORCID to comment.