Many-Objectives Optimization: A Machine Learning Approach for Reducing the Number of Objectives
نویسندگان
چکیده
Solving real-world multi-objective optimization problems using Multi-Objective Optimization Algorithms becomes difficult when the number of objectives is high since types algorithms generally used to solve these are based on concept non-dominance, which ceases work as grows. This problem known curse dimensionality. Simultaneously, existence many objectives, a characteristic practical problems, makes choosing solution very difficult. Different approaches being in literature reduce required for optimization. aims propose machine learning methodology, designated by FS-OPA, tackle this problem. The proposed methodology was assessed DTLZ benchmarks suggested and compared with similar algorithms, showing good performance. In end, applied real polymer processing, its effectiveness. algorithm has some advantages (NL-MVU-PCA), namely, possibility establishing variable–variable objective–variable relations (not only objective–objective), elimination need define/chose kernel neither optimize parameters. collaboration DM(s) allows obtainment explainable solutions.
منابع مشابه
Fast optimization of non-convex Machine Learning objectives
In this project we examined the problem of non-convex optimization in the context of Machine Learning, drawing inspiration from the increasing popularity of methods such as Deep Belief Networks, which involve non-convex objectives. We focused on the task of training the Neural Autoregressive Distribution Estimator, a recently proposed variant of the Restricted Boltzmann Machine, in applications...
متن کاملEfficient optimization of many objectives by approximation-guided evolution
Multi-objective optimization problems arise frequently in applications, but can often only be solved approximately by heuristic approaches. Evolutionary algorithms have been widely used to tackle multi-objective problems. These algorithms use different measures to ensure diversity in the objective space but are not guided by a formal notion of approximation. We present a framework for evolution...
متن کاملConditions for Convergence in Regularized Machine Learning Objectives
Analysis of the convergence rates of modern convex optimization algorithms can be achived through binary means: analysis of emperical convergence, or analysis of theoretical convergence. These two pathways of capturing information diverge in efficacy when moving to the world of distributed computing, due to the introduction of non-intuitive, non-linear slowdowns associated with broadcasting, an...
متن کاملDesign and evaluation of a national set of learning objectives: the medical physiology learning objectives project.
In 1998, the American Physiological Society (APS) and the Association of Chairs of Departments of Physiology (ACDP) began collaboration on a project to develop a set of physiology learning objectives for medical students. Over the next 2 years, more than 50 physiologists collaborated in the development a comprehensive draft containing its 695 learning objectives. Faculty in 31 medical schools i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematical and computational applications
سال: 2023
ISSN: ['1300-686X', '2297-8747']
DOI: https://doi.org/10.3390/mca28010017