English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

Forum topic · 小凯 · 2026-07-08

Summary

This paper introduces TabPack, an efficient hyperparameter ensemble of multilayer perceptrons (MLPs) for tabular deep learning. Existing MLP ensembles apply identical hyperparameters to every member model, requiring expensive hyperparameter tuning to reach peak performance. TabPack samples and trains multiple MLPs with diverse hyperparameters in a single run, dynamically selecting ensemble members during training. Experiments show that TabPack's default configuration matches the performance of previously tuned state-of-the-art methods on tabular benchmarks while drastically reducing the computational cost and engineering effort needed to achieve competitive results. Notably, running the default TabPack setup on a modern MacBook can be faster than tuning certain baseline models on industrial-grade GPUs. The work lowers the practical barrier to deploying strong deep learning models on tabular data by combining ensembling, hyperparameter diversity, and dynamic member selection in one efficient framework.

Paper Overview

  • Field: Machine Learning
  • Authors: Yury Gorishniy, Akim Kotelnikov, Ivan Rubachev, Artem Babenko
  • Posted: 2026-07-06
  • arXiv: 2607.05380
  • Summary

    In tabular deep learning, efficient ensembles of multilayer perceptrons (MLPs) have recently become a practical and effective architecture. Existing approaches use the same hyperparameters for all underlying MLPs, so reaching peak performance requires dedicated hyperparameter tuning.

    This paper proposes TabPack, an efficient MLP ensemble with strong out-of-the-box performance that reduces dependence on traditional tuning. Within a single run, TabPack efficiently samples and trains multiple MLPs with diverse hyperparameters in parallel and dynamically selects ensemble members during training.

    Key points

  • Problem with prior MLP ensembles: all member models share identical hyperparameters, so competitive performance requires costly per-dataset hyperparameter search.
  • TabPack approach: in one run, it samples and trains many MLPs with varied hyperparameters in parallel, then dynamically picks ensemble members as training progresses.
  • Out-of-the-box performance: default TabPack achieves results comparable to previously published methods that were extensively tuned, while needing far less compute and engineering effort on tabular tasks.
  • Compute efficiency: running the default TabPack configuration on a modern MacBook can take less wall-clock time than tuning certain baselines on an industrial-grade GPU.
  • Practical impact: lowers the barrier to deploying strong deep tabular models by combining ensembling, hyperparameter diversity, and dynamic member selection in a single efficient framework.
  • Resources

  • Paper: https://arxiv.org/abs/2607.05380

Tags

#tabular-deep-learning#mlp-ensemble#hyperparameter-tuning#machine-learning#arxiv#model-ensembling#deep-learning#benchmark

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