TabPack packs MLPs with diverse sampled hyperparameters into one vectorized model, selects ensemble members online during training, and matches tuned baselines at a fraction of the compute cost.
Advances in Neural Information Processing Systems , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
A multi-source extension of constrained Max-value Entropy Search for Bayesian optimization incorporates auxiliary data sources to improve early exploration and performance under constraints even with weak correlations.
citing papers explorer
-
TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning
TabPack packs MLPs with diverse sampled hyperparameters into one vectorized model, selects ensemble members online during training, and matches tuned baselines at a fraction of the compute cost.
-
Constrained Bayesian Optimisation with Multiple Information Sources
A multi-source extension of constrained Max-value Entropy Search for Bayesian optimization incorporates auxiliary data sources to improve early exploration and performance under constraints even with weak correlations.