【学术视频】统计物理与神经计算国际研讨会 | 东京工业大学Takashi Takahashi博士

更多精彩视频登陆网站

www.koushare.com

图 | Takashi Takahashi

题   目：Replicated vector approximate message passing for resampling problem

报告人：Takashi Takahashi

单   位：Tokyo Institute of Technology

时   间：2019-10-06

地   点：中山大学

扫码观看精彩报告视频

报告摘要

Resampling techniques are widely used in statistical inference and ensemble learning, in which estimators' statistical properties are essential. However, existing methods are computationally demanding, because repetitions of estimation/learning via numerical optimization/integral for each resampled data are required. In this study, we introduce a computationally efficient method to resolve such problem: replicated vector approximate message passing. This is based on a combination of the replica method of statistical physics and an accurate approximate inference algorithm, namely the vector approximate message passing of information theory. The method provides tractable densities without repeating estimation/learning, and the densities approximately offer an arbitrary degree of the estimators' moment in practical time. In the experiment, we apply the proposed method to the stability selection method, which is commonly used in variable selection problems. The numerical results show its fast convergence and high approximation accuracy for problems involving both synthetic and real-world datasets.

个人简介

Takashi Takahashi is  a Ph.D. student in Mathematical and Computing Science at Tokyo Institute of Technology, where he is advised by Yoshiyuki Kabashima. He works in the fields of statistical mechanics of disordered systems and statisitcal inference.

会议简介

2019年10月4日-6日，统计物理与神经计算国际研讨会由中山大学物理学院主办，这是在该校举办的第一届物理，机器学习与计算神经科学交叉的国际会议，会议邀请了这一领域近年来作出杰出贡献的国内外专家参与讨论，并围绕神经网络的计算建模，理论研究，生物机制的最新进展展开。

—— ——往期精彩回顾—— ——●【学术视频】统计物理与神经计算国际研讨会 | 北京大学吴思教授：Push-pull feedback implements rough-to-fine information retrieval●【学术视频】统计物理与神经计算国际研讨会 | Adriano Barra of Università del Salento: Guerra's interpolation in machine learning & neural networks●【学术视频】统计物理与神经计算国际研讨会 | Taro Toyoizumi of RIKEN CBS:Exploring the learning principle in the brain●【学术视频】统计物理与神经计算国际研讨会 | 英国阿斯顿大学David Saad教授：Function-Space Entropy in Deep-Learning Networks●【学术视频】统计物理与神经计算国际研讨会 | Alexis Dubreuil: Disentangling the roles of dimensionality and cell classes in neural computation

为满足更多科研工作者的需求，蔻享平台开通了各科研领域的微信交流群。

进群请添加微信：18256943123

小编拉您入群哟！

未经许可，禁止转载本页内容

转载授权请微信联系：18256943123

戳这里，观看精彩视频哟！