Summary
TabPack is a new approach for efficient MLP ensembles in tabular deep learning, proposed by Yury Gorishniy, Akim Kotelnikov, Ivan Rubachev, and Artem Babenko (arXiv:2607.05380). While efficient MLP ensembles are already a practical and effective architecture for tabular data, existing methods apply identical hyperparameters to all underlying MLPs and rely on hyperparameter tuning for best performance. TabPack instead delivers strong out-of-the-box performance with minimal tuning. In a single run, it efficiently samples and trains multiple MLPs with different hyperparameters in parallel and dynamically selects ensemble members during training. Experiments show that TabPack with default settings matches extensively tuned prior methods, substantially reducing the effort and compute needed to reach competitive results on tabular tasks. Notably, the default TabPack configuration runs faster on a modern MacBook than tuning certain baselines on industrial-grade GPUs.
Paper Overview
Field: ML
Authors: Yury Gorishniy, Akim Kotelnikov, Ivan Rubachev, Artem Babenko
Published: 2026-07-06
arXiv:
2607.05380Summary
Efficient ensembles of MLPs have recently become an effective and practical architecture for deep learning on tabular data. Existing approaches use the same hyperparameters for all underlying MLPs, and achieving optimal performance requires hyperparameter tuning.
This paper introduces TabPack, an efficient MLP ensemble with strong out-of-the-box performance that reduces dependence on traditional tuning. In a single run, TabPack efficiently samples and trains multiple MLPs with different hyperparameters in parallel, and dynamically selects ensemble members during training.
Key Findings
- TabPack with default settings performs on par with extensively tuned prior methods.
- It significantly reduces the effort and computational resources required to achieve competitive results on tabular tasks.
- Notably, running the default TabPack configuration on a modern MacBook takes less time than tuning certain baselines on industrial-grade GPUs.
Link:
arXiv:2607.05380
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178346203