---
title: "TabPack：面向表格深度学习的高效超参数集成方法"
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集成","TabPack","表格深度学习","超参数调优"]
---

# TabPack：面向表格深度学习的高效超参数集成方法

## AI 点评

> 这篇论文解决了表格深度学习中的一个实际痛点：超参数调优。TabPack 的设计思路非常巧妙——与其调优一个模型，不如并行训练一批不同超参数的模型并动态选择集成员。我认为这对非深度学习专家尤其重要，他们往往无法花大量精力调参。默认配置就能在普通笔记本上跑出好结果，这降低了应用门槛。如果你在做表格数据的 AutoML 或生产级模型部署，TabPack 非常值得关注。

## 速览

TabPack 是一种用于表格数据的高效 MLP 集成方法，通过单次运行并行采样并训练多个不同超参数的 MLP，并在训练中动态选择集成成员，大幅降低了对超参数调优的依赖。实验表明，默认配置下的 TabPack 在中等至大规模公开数据集上能达到与精细调优的基线方法相当的性能，且计算资源消耗显著减少——在 MacBook 上运行默认配置甚至比在工业级 GPU 上调优某些基线更快。

## 关键点

- TabPack 在单次运行中并行训练多个不同超参数的 MLP，并动态选择子集作为集成。
- 用户只需指定超参数采样范围，无需精确调优，降低了使用门槛。
- 默认配置在中等至大规模表格数据集上达到与精心调优方法相当的精度。
- 计算效率极高，MacBook 上的默认运行甚至快于某些基线在 GPU 上的调优过程。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_fd1d757fec221f9dfcf051d6