AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Quantum Bayesian Optimization

Zhongxiang Dai, Gregory Kang Ruey Lau, Arun Verma, Yao Shu, Bryan Kian Hsiang Low, Patrick Jaillet

NeurIPS 2023 · Probabilistic and scientific modeling › Bayesian optimization · approach: Regret bounds for Bayesian optimization · 2 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
replace classical GP-UCB with Q-GP-UCB (quantum Monte Carlo observations)Q-GP-UCB · Synthetic, bounded (Bernoulli) noise, SE-kernel GP sample, 20 pointscumulative regretImproved
replace classical GP-UCB with Q-GP-UCBQ-GP-UCB · Synthetic, Gaussian noisecumulative regretImproved
replace classical GP-UCB with Q-GP-UCBQ-GP-UCB · AutoML SVM hyperparameter tuningcumulative regretImproved
use kernelized (GP) bandits instead of linear bandits (LinUCB, Q-LinUCB)Q-GP-UCB and GP-UCB · Synthetic non-linear reward and AutoMLcumulative regretImproved
add simulated IBM quantum noise model to the Qiskit simulationQ-GP-UCB · Synthetic experiment with noisy quantum simulationcumulative regretHurt
run on a real quantum computer instead of simulated noiseQ-GP-UCB · Synthetic experiment on real quantum hardwarecumulative regretHurt
replace quantum Monte Carlo with classical MC estimation (theory) (ablation)Q-GP-UCB · regret bound analysisregret upper boundHurt
use the tighter confidence ellipsoid analysis for Q-LinUCBQ-LinUCB · regret bound (theory)regret upper boundImproved

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