Výsledky vyhledávání - "MARQUIS, CHRISTOPHER"

Report

Using Mixed-Effects Models to Learn Bayesian Networks from Related Data Sets

Autor: Scutari, Marco, Marquis, Christopher, Azzimonti, Laura

Publikováno v: Proceedings of Machine Learning Research 186 (PGM 2022), 73-84

We commonly assume that data are a homogeneous set of observations when learning the structure of Bayesian networks. However, they often comprise different data sets that are related but not homogeneous because they have been collected in different w

Externí odkaz: http://arxiv.org/abs/2206.03743

Zobrazit plný text záznamu

Akademický článek

History Matters for Organizations: An Integrative Framework for Understanding Influences from the Past.

Autor: Marquis, Christopher¹ (AUTHOR), Qiao, Kunyuan² (AUTHOR)

Publikováno v: Academy of Management Review. Jul2023, p1-27. 27p.

Zobrazit plný text záznamu

Report

An initial alignment between neural network and target is needed for gradient descent to learn

Autor: Abbe, Emmanuel, Cornacchia, Elisabetta, Hązła, Jan, Marquis, Christopher

Publikováno v: Proceedings of the International Conference on Machine Learning, 2022

This paper introduces the notion of ``Initial Alignment'' (INAL) between a neural network at initialization and a target function. It is proved that if a network and a Boolean target function do not have a noticeable INAL, then noisy gradient descent

Externí odkaz: http://arxiv.org/abs/2202.12846

Zobrazit plný text záznamu