Parallel Multiobjective Optimization

Speaker:  Enrique Alba – Malaga, Spain
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

This lecture introduces the basic concepts of two fields of research: Parallelism and Multiobjective optimization. Dealing with complex problems means optimizing a given metric, like the error when doing machine learning. There are many algorithms and tools to do so, but usually the plain basic concepts found in science are weak so as to solve real world problems.

Amongst the many ways to improve existing techniques, we here focus on the mentioned two. First, multiobjective modeling of complex problems is a main avenue for including the real features and preferences of the designer into the computer tools used. Because of the added complexity, and because of the naturally heavy requirements of big data and processes, parallelism comes handy as a privileged way to have a solution in affordable times, and even as a new way of building multiobjective algorithms of higher accuracy and diverse Pareto fronts.

We will revise the main concepts, tools, metrics, open issues, and application domains related to parallel models of search, optimization, and learning techniques. We also will describe new techniques and trends in multiobjective research in relation to metaheuristics. Facts, methodology, and general open issues will be presented in this talk.

About this Lecture

Number of Slides:  45
Duration:  60 minutes
Languages Available:  English, Spanish
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.