报告时间：2021年3月24日 下午16:00-17:00
报告形式：腾讯会议
会议ID：775 876 088
会议链接：https://meeting.tencent.com/l/z7M3MKZrJxPe
报告嘉宾：廖振宇
报告主题：Performance-complexity trade-off in large dimensional spectral clustering
报告摘要
The big data revolution comes along with the challenging need to parse, mine, compress large amount of large dimensional data. Many modern machine learning algorithms (including state-of-the-art deep neural networks) are designed to work with compressed, quantized, or even binarized data/features so that they can run on low-power IoT devices.In this talk, we will focus on the theoretical analysis of spectral clustering method that aims to find possible clusters from a given data matrix in an unsupervised manner, by exploring the informative eigenstructure (e.g., the dominant eigenvector) of the data matrix. Random matrix analysis reveals the surprising fact that very little change occurs in the informative eigenstructure even under drastic sparsification and/or quantization, and consequently that very little downstream performance loss occurs with very aggressively uniformed and non-uniformed, sparsified and/or quantized spectral clustering. The present study is based on a spiked model analysis of nonlinear random matrices and may be of independent research interest. We expect that our analysis opens the door to improved analysis of computationally efficient methods for large dimensional machine learning and neural network models more generally.
个人简介
廖振宇博士目前是加州大学伯克利分校的博士后，合作导师是Michael Mahoney，即将入职华中科技大学任副教授。廖振宇博士于2014年本科毕业于华中科技大学，2016年于巴黎萨克雷大学获硕士学位，2019年博士毕业于巴黎萨克雷大学，导师是Romain Couillet教授和Yacine Chitour教授，专业是统计与机器学习。廖振宇博士的研究兴趣包括机器学习、信号处理、随机矩阵理论和高维统计。廖振宇博士于2019年获得巴黎萨克雷大学的ED STIC Ph.D. Student Award，于2016年获得 Supélec Foundation Ph.D. Fellowship。廖振宇博士在IEEE Transactions on Signal Processing，The Annals of Applied Probability等学术期刊与ICLR, NeurIPS, ICML等学术会议上发表学术论文10余篇。廖振宇博士担任加拿大自然科学和工程研究理事会外部评审专家以及JMLR, IEEE TPAMI, IEEE TSP, NeurIPS, ICML, ICLR, AAAI等期刊和会议的审稿人。
扫描下方二维码报名↘
所有消息会在两个群中同步通知
请大家不要重复加群~
