---
title: "TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.05380v1"
permalink: "https://feed.astralor.com/items/itm_fd1d757fec221f9dfcf051d6"
published: "2026-07-06T17:55:55.000Z"
score: 80
channel: "ai"
tags: ["MLP Ensemble","TabPack","Tabular Deep Learning","Hyperparameter Tuning"]
---

# TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

## AI commentary

> This paper addresses a practical pain point in tabular deep learning: hyperparameter tuning. TabPack's design is clever—instead of tuning one model, it trains a batch of models with different hyperparameters in parallel and dynamically selects ensemble members. I think this is especially important for non-experts who cannot afford extensive tuning. Getting good results with default settings on a regular laptop lowers the barrier. If you are working on AutoML for tabular data or deploying production models, TabPack is definitely worth a look.

## At a glance

TabPack is an efficient MLP ensemble method for tabular data that samples and trains many MLPs with different hyperparameters in parallel in a single run, selecting ensemble members on the fly. This greatly reduces reliance on hyperparameter tuning. Experiments on medium-to-large public datasets show that default TabPack performs on par with extensively tuned baselines while using substantially less compute—running the default config on a MacBook took less time than tuning some baselines on an industry-grade GPU.

## Key points

- TabPack trains many MLPs with diverse hyperparameters in parallel in a single run, dynamically selecting ensemble members.
- Users only need to specify sampling ranges for hyperparameters, eliminating manual tuning.
- Default config achieves accuracy comparable to extensively tuned baselines on medium-to-large tabular datasets.
- Extremely compute-efficient: default run on a MacBook outperforms tuning of some baselines on an industry GPU in speed.

## Full text

In deep learning for tabular data, efficient ensembles of multilayer perceptrons (MLPs) have recently emerged as effective and practical architectures. Existing methods of this kind use the same hyperparameters for all underlying MLPs, which requires hyperparameter tuning for achieving the best performance. In this work, we introduce TabPack, an efficient MLP ensemble with strong out-of-the-box performance and reduced reliance on traditional tuning. In a single run, TabPack samples and trains many MLPs with different hyperparameters efficiently in parallel and selects ensemble members on the fly during training. Thus, TabPack only requires specifying ranges from which to sample MLP hyperparameter rather than exact hyperparameter values, which naturally demands less precision for good performance. In experiments on medium-to-large public datasets, TabPack with default settings performs on par with extensively tuned prior methods, thus substantially reducing effort and compute resources needed to achieve competitive results on tabular tasks. Notably, running the default TabPack configuration on a modern MacBook took less time than tuning some baselines on an industry-grade GPU.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_fd1d757fec221f9dfcf051d6