AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

GIBBON: General-purpose Information-Based Bayesian Optimisation

Henry B. Moss, David S. Leslie, Javier Gonzalez, Paul Rayson

JMLR 2021 · Probabilistic and scientific modeling › Bayesian optimization · approach: Local and high-dimensional Bayesian optimization · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 exact Thompson-sampled max-values instead of Gumbel samples (ablation)GIBBON · noisy Hartmann, B=5regret: small boost for batch, no effect for B=1Mixed
use exact Thompson-sampled max-values instead of Gumbel samples (ablation)GIBBON · noisy Hartmanncomputational overhead: five and three times the cost for B=1 and B=5Hurt
increase batch size beyond 25 (ablation)GIBBON · noisy Hartmann (20 iterations)regretHurt
increase batch size to 50 with local penalisation (ablation)LPEI · noisy Hartmann (20 iterations)regretImproved
down-weight diversity term by factor B^2 (ablation)GIBBON · noisy Hartmann, large batchesregretImproved
use GIBBON instead of MES in noiseless sequential caseGIBBON · Shekel (d=4)regretImproved
use GIBBON instead of KG for batch BOGIBBON · synthetic batch benchmarkscomputational overhead: at least 10 times smallerImproved
use GIBBON instead of MUMBOGIBBON · multi-fidelity synthetic benchmarksregret and overheadImproved
use GIBBON instead of MFMESGIBBON · synthetic benchmarksfinal regretImproved
use DPP-based batch heuristic DPPEI instead of GIBBONDPPEI · synthetic batch benchmarksregretHurt
increase number of BO stepsbatch KG, MFMES, NEI vs GIBBON · Hartmanncomputational overheadMixed

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