时间:5月16日14:00-16:00
地点:管楼216会议室
题目:Resource-Constrained Expensive Optimization: Challenges, Methods and Applications
报告摘要
Expensive optimization deals with problems in which candidate solutions are evaluated by conducting experiments, e.g. physical or biochemical experiments or time-consuming computer simulations. Although this form of optimization is becoming more popular across the sciences, it may be subject to unexplored resourcing issues, as any experiment may require resources to be conducted. This talk will introduce several resourcing issues that I have encountered in my work with experimentalists and industry, including ephemeral resource constraints, changing variables, unsafe environments, and heterogeneous objectives. For an optimizer, these issues result in an environment that is weirdly dynamic, constrained, and/or multi-objective. Different optimization methods designed to cope with these resourcing issues will be described, and practical applications introduced to motivate the issues.
报告人简介
Professor Richard Allmendinger is Associate Dean for Business Engagement, Civic & Cultural Partnerships in the Faculty of Humanities, and Professor of Applied Artificial Intelligence at The University of Manchester.
His research interests are in the field of data science and in particular in the development and application of optimization and machine learning techniques to real-world problems arising in areas such as healthcare, manufacturing, engineering, economics, sports, music, and forensics. He has been awarded around £48m as PI or co-I in research funding by UK funding bodies (e.g. ESRC, EPSRC, Innovate UK) and industrial partners, led the commercialisation of products, and is currently establishing a spinout focused on establishing safe programming code. He has published over 80 articles, including several ones in ABS4 Journals including EJOR, IEEE TEC, etc.
He is also co-Lead of the North West Productivity Forum, External Examiner for Warwick Business School, Senior Member of the IEEE, Vice-Chair of the IEEE Bioinformatics and Bioengineering Technical Committee, Editorial Board Member of several international journals, Senior Scientist at Eharo, Advisor for Prevayl, and AI Advisor for the first dedicated AI fund in the North of UK, which is managed by local private equity company River Capital.
Prior to Manchester, he was Honorary Lecturer and Research Associate at the Biochemical Engineering Department, University College London. He studied Business Engineering at the Karlsruhe Institute of Technology and the Royal Melbourne Institute of Technology and completed a PhD in Computer Science (Machine Learning & Optimization) at The University of Manchester.