随波逐流:序列蒙特卡罗方法中的最优传输方法和神经网络应用 Going with flow: transport methods and neural networks for sequential Monte Carlo methods主讲人:英国萨里大学李云鹏副教授

时间:2021-12-16         阅读:

光华讲坛——海外名家讲堂

主题:随波逐流:序列蒙特卡罗方法中的最优传输方法和神经网络应用

Going with flow: transport methods and neural networks for sequential Monte Carlo methods主讲人:英国萨里大学李云鹏副教授

主持人:拉斯维加斯平台网金融科技国际联合实验室兼职教授 杨永鑫

时间:2021年12月21日(周二)下午17:00

举办地点:腾讯会议号263499773

主办单位:金融科技国际联合实验室 科研处

主讲人简介

李云鹏,萨里大学计算机系副教授,博导。主要研究领域为统计机器学习和信号处理,尤其是贝叶斯推断和蒙特卡洛方法,以及他们在交叉学科应用:如疾病检测、环境感知、物体追踪等。他于2017年毕业于加拿大麦吉尔大学,后于牛津大学从事博士后研究。

Yunpeng Li is a Senior Lecturer in Artificial Intelligence in the Department of Computer Science at the University of Surrey in the UK. His research interests are in the areas of statistical machine learning and signal processing, particularly Bayesian inference techniques and Monte Carlo sampling methods. He has broad interests in interdisciplinary applications of machine learning including disease detection, environmental sensing and object tracking. He received a PhD in Electrical Engineering at the McGill University in Canada in 2017 and was a Junior Research Fellow at the University of Oxford in 2018.

内容简介

非线性和非高斯状态空间中的序列状态估计在信号处理和统计中具有广泛的应用。粒子滤波,又名序列蒙特卡罗方法,是一种有效的贝叶斯非线性序列状态估计方法。然而其在高维滤波场景中受到权重退化的影响,并且通常需要已知运动模型和测量模型。我首先将介绍一种新的粒子滤波算法,通过求解偏微分方程使粒子从先验分布不断迁移到后验分布,并通过粒子滤波框架来纠正迁移过程中的误差。随后我将介绍通过神经网络学习粒子滤波中的模型和提议分布,使其适用于大规模实际应用。

Sequential state estimation in non-linear and non-Gaussian state spaces has a wide range of applications in signal processing and statistics. One of the most effective non-linear filtering approaches, particle filters a.k.a. sequential Monte Carlo methods, suffer from weight degeneracy in high-dimensional filtering scenarios. Several avenues have been pursued to address high dimensionality. Among these, particle flow filters migrate particles continuously from the prior distribution to the posterior distribution by solving partial differential equations. In the first part of the talk, I will present new filters which incorporate deterministic particle flows into an encompassing particle filter framework. The valuable theoretical guarantees concerning particle filter performance still apply, but we can exploit the attractive performance of the particle flow methods. The second part of the talk will focus on learning different components of particle filters through neural networks, to provide flexibility to apply particle filters in large-scale real-world applications.