AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

$\alpha$-PFN: Fast Entropy Search via In-Context Learning

Herilalaina Rakotoarison, Steven Adriaensen, Tom Julian Viering, Carl Hvarfner, Samuel Müller, Frank Hutter, Eytan Bakshy

ICML 2026 · Probabilistic and scientific modeling › Bayesian optimization · approach: Local and high-dimensional Bayesian 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
replace MC-based GP entropy search (MES) with an alpha-PFN that predicts the acquisition in one forward passMES · HPO-B-7609 (9D)speedup: 74.5 -> 1.1 minutes (65.0x)Improved
replace MC-based GP entropy search with alpha-PFN across variantsJES, MES, PES · synthetic, LCBench and HPO-B tasksruntime: speedups from 1.6x to over 72xImproved
alpha-PFN approximation of PES, MES and JES in place of GP-MCMC versionsentropy search acquisition · synthetic functions, inference regretinference regretNo clear effect
alpha-PFN JES versus GP baselines on real HPO tasksJES · LCBench and HPO-Bpredicted best accuracy / average rankImproved
alpha-PFN MES versus GP MESMES · HPO-Baverage rank of inference regretHurt
alpha-PFN variants versus GP on HartmannJES, MES · Hartmann 4D vs 6Dinference regretMixed
train with clustered BO-like traces instead of uniformly sampled context and query points (ablation)alpha-PFN · higher-dimensional synthetic functionsinference regretImproved
increase observation noise to 0.5 (out of distribution) at test time (ablation)alpha-PFN and GP baselines · Hartmann 4D and 6Dinference regret: sigma_n 0.316 -> 0.5Hurt
train a second-stage alpha-PFN on information gains instead of Monte Carlo averaging of base-PFN at inference (ablation)alpha-PFN · 1D JES qualitative comparisoninformation gain estimate noiseImproved

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