atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Local Latent Space Bayesian Optimization over Structured Inputs

NeurIPS 2022 · Probabilistic and scientific modeling › Bayesian optimization · approach: Local and high-dimensional Bayesian optimization · 11 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SELFIES transformer VAE instead of JTVAE (ablation)LOL-BO · penalized logPlogP: 123.54 -> 545.17Helped
add joint training of encoder/GP (LOL-BO) to fixed-latent TuRBO (ablation)TuRBO SELFIES · DRD3 docking, 5000 evalsdocking score: -13.0 -> -15.4Helped
use local trust-region BO instead of standard global LS-BO (ablation)LS-BO SELFIES · DRD3 docking, 5000 evalsdocking score: -12.6 -> -13.0Helped
use LOL-BO instead of T-LBOlatent BO · expressionsfinal regret: 0.194 -> 0.079Helped
use SELFIES VAE instead of JTVAE (ablation)latent BO · GuacaMol reconstructionreconstruction accuracy: 0.767 -> 0.913Helped
use SELFIES VAE instead of JTVAE (ablation)latent BO · decoding noisedecode stddev: 0.1 -> 0.04Helped
use LOL-BO instead of Graph-GA at large budgetLOL-BO SELFIES · DRD3 docking, 5000 evalsdocking score: -16.5 -> -15.4Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy