English(EN) Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping

新研究重新审视表格数据的深度学习回归目标

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

一篇新的研究论文重新审视了表格数据的深度学习回归目标，发现虽然分位数损失（Quantile Loss）相比均方误差（MSE）提供了持续的改进，但单一的全局提前停止点仍然会限制性能。该研究通过使用与输入相关的标签平滑（input-dependent label smoothing）来引入分位数损失的异方差感知扩展（heteroskedasticity-aware extension），以解决这一局限性。该研究提供了表格深度学习回归目标的最新经验视图，并将其代码发布在Hugging Face上。 AI

影响为表格深度学习中的回归目标提供了最新的经验见解，有可能在这些常见场景中提高模型性能。

排序理由关于机器学习技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于机器学习技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev, Ivan Rubachev, Daniil Krasylnikov, Artem Babenko · 2026-10-12 04:00

重新审视表格深度回归：目标与全局提前停止的局限性

arXiv:2610.13909v1 Announce Type: cross Abstract: While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer a…

本文如何被排名

报道来源 [1]

重新审视表格深度回归：目标与全局提前停止的局限性

相关实体

相关话题