AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

DABO: Difficulty-Aware Bayesian Optimization with Diffusion-Learned Priors

Mengyang Li, Pinlong Zhao

CVPR 2026 · Probabilistic and scientific modeling › Bayesian optimization · approach: Multi-fidelity hyperparameter optimization

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
add diffusion-generated training data to ifBO (ablation)ifBO · LCBench (ablation)final normalized regret: 0.016 -> 0.0152Improved
add difficulty conditioning in the PFN (ablation)ifBO · LCBench (ablation)final normalized regret: 0.016 -> 0.0148Improved
add difficulty-adaptive acquisition (ablation)ifBO · LCBench (ablation)final normalized regret: 0.016 -> 0.0154Improved
combine diffusion data with difficulty conditioning (ablation)ifBO · LCBench (ablation)final normalized regret: 0.016 -> 0.0142Improved
add all three difficulty-aware components (ablation)ifBO · LCBench (ablation)final normalized regret: 0.016 -> 0.0140Improved
difficulty-aware PFN trained on diffusion data vs FT-PFNFT-PFN · PD1 surrogatelog-likelihood: 1.13 -> 2.50Improved
difficulty-aware PFN vs FT-PFN on MSEFT-PFN · Taskset surrogateMSE: 0.004 -> 0.0042No clear effect
difficulty-aware PFN vs FT-PFN inference timeFT-PFN · Surrogate runtimeruntime (sec): 0.72 -> 2.05Hurt
replace hand-crafted basis functions with diffusion-learned priorsifBO · Synthetic curve fidelityFCD: 2.83 -> 1.24Improved
DABO vs ifBO on PD1 final regretifBO · PD1final normalized regret: 0.034 -> 0.028Improved
DABO vs ifBO on easy tasksifBO · 75 HPO tasksregretNo clear effect

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