BBOmix is the first open tabular benchmark for hyperparameter optimization of unsupervised autoencoder representation learning on TCGA and SCHC omics data, with 105k evaluations, reconstruction-downstream correlation measurements, and baselines for single-fidelity, multi-fidelity, and transfer HPO m
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
BBO-Pile is the first large-scale open dataset of real optimization trajectories used to train and scale foundation models that imitate black-box optimization methods.
citing papers explorer
-
BBOmix: A Tabular Benchmark for Hyperparameter Optimization of Unsupervised Biological Representation Learning
BBOmix is the first open tabular benchmark for hyperparameter optimization of unsupervised autoencoder representation learning on TCGA and SCHC omics data, with 105k evaluations, reconstruction-downstream correlation measurements, and baselines for single-fidelity, multi-fidelity, and transfer HPO m
-
An Open-Source Training Dataset for Foundation Models for Black-box Optimization
BBO-Pile is the first large-scale open dataset of real optimization trajectories used to train and scale foundation models that imitate black-box optimization methods.