AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Preferential Bayesian Optimization

Javier González, Zhenwen Dai, Andreas Damianou, Neil D. Lawrence

ICML 2017 · Probabilistic and scientific modeling › Bayesian optimization · approach: Acquisition function design · 36 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 GP-based preferential Bayesian optimization with dueling-Thompson samplingPreferential optimization on Forrester, Six-Hump Camel, Gold-Stein, and Levy · Four objective-function benchmarkstrue objective value at the current Condorcet winnerImproved
Model correlations across arms with a GP rather than using SparringSix-Hump Camel · Six-Hump Camelspeed of finding the optimumImproved
Use interactive Bayesian optimization with a greedy acquisitionInteractive Bayesian optimization (IBO) · Four objective-function benchmarkstrue objective value at the current Condorcet winnerHurt
Choose duels uniformly at randomRandom policy · Four objective-function benchmarkstrue objective value at the current Condorcet winnerHurt
Use bandit methods that do not model correlations across armsSparring · Discrete benchmark gridsevaluations needed to convergeHurt
Use pure exploration instead of dueling-Thompson sampling (ablation)PBO · Four objective-function benchmarkstrue objective value at the current Condorcet winnerHurt
Use Copeland Expected Improvement instead of dueling-Thompson sampling (ablation)PBO · Forrestertrue objective value at the current Condorcet winnerHurt
Use dueling-Thompson sampling rather than pure exploration or Copeland Expected Improvement (ablation)PBO · Forrester, Six-Hump Camel, Gold-Stein, and Levytrue objective value at the current Condorcet winnerImproved
Use Bernoulli outcome variance as the exploration signal rather than latent-function uncertainty (ablation)PBO pure-exploration acquisition · Duel spaceability to avoid revisiting observed duelsHurt

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