AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

A Quantile-based Approach for Hyperparameter Transfer Learning

David Salinas, Huibin Shen, Valerio Perrone

ICML 2020 · Probabilistic and scientific modeling › Bayesian optimization · approach: Acquisition function design · 14 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 Gaussian Copula normalization and a parametric prior in a Gaussian Copula ProcessHyperparameter optimization · DeepARDTM normalized over random search: 0.00 -> 0.73Improved
Use Gaussian Copula normalization and a parametric prior in a Gaussian Copula ProcessHyperparameter optimization · FCNETDTM normalized over random search: 0.00 -> 0.94Improved
Use Gaussian Copula normalization and a parametric prior in a Gaussian Copula ProcessHyperparameter optimization · XGBoostDTM normalized over random search: 0.00 -> 0.37Improved
Use Gaussian Copula normalization and a parametric prior in a Gaussian Copula ProcessHyperparameter optimization · NAS-Bench-201DTM normalized over random search: 0.00 -> 0.94Improved
Add a parametric prior to Gaussian Copula Process (ablation)GCP · DeepARDTM normalized over random search: 0.42 -> 0.73Improved
Add a parametric prior to Gaussian Copula Process (ablation)GCP · FCNETDTM normalized over random search: 0.79 -> 0.94Improved
Add a parametric prior to Gaussian Copula Process (ablation)GCP · XGBoostDTM normalized over random search: 0.31 -> 0.37Improved
Add a parametric prior to Gaussian Copula Process (ablation)GCP · NAS-Bench-201DTM normalized over random search: 0.45 -> 0.94Improved
Use Gaussian Copula normalization instead of standardization with a parametric prior (ablation)Thompson sampling · FCNETDTM normalized over random search: -563.27 -> 0.83Improved
Use Gaussian Copula normalization instead of standardization with a parametric prior (ablation)Gaussian process with parametric prior · FCNETDTM normalized over random search: -166.64 -> 0.94Improved
Add a Gaussian Copula parametric prior to use transfer informationCopula-based hyperparameter optimization · DeepAR with a dissimilar target taskDTM normalized over random searchMixed
Adapt the transfer prior with observations from the current task using GCP (ablation)CTS · DeepAR and XGBoostDTMImproved

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