Výsledky vyhledávání

Report

Why In-Context Learning Transformers are Tabular Data Classifiers

Autor: Breejen, Felix den, Bae, Sangmin, Cha, Stephen, Yun, Se-Young

The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. As synthetic data does not share features or labels with real-world data, the underlying mechanism that contri

Externí odkaz: http://arxiv.org/abs/2405.13396

Zobrazit plný text záznamu

Report

Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning

Autor: Breejen, Felix den, Bae, Sangmin, Cha, Stephen, Kim, Tae-Young, Koh, Seoung Hyun, Yun, Se-Young

While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore the innovative retrieval mechanism, a methodology that allows neural n

Externí odkaz: http://arxiv.org/abs/2311.07343

Zobrazit plný text záznamu

Report

A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search

Autor: Cha, Stephen, Kim, Taehyeon, Lee, Hayeon, Yun, Se-Young

This survey focuses on categorizing and evaluating the methods of supernet optimization in the field of Neural Architecture Search (NAS). Supernet optimization involves training a single, over-parameterized network that encompasses the search space o

Externí odkaz: http://arxiv.org/abs/2204.03916

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání