scholarly journals Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization

2020 ◽  
Vol 34 (06) ◽  
pp. 10044-10052 ◽  
Author(s):  
Syrine Belakaria ◽  
Aryan Deshwal ◽  
Nitthilan Kannappan Jayakodi ◽  
Janardhan Rao Doppa
Keyword(s):  
Optimization Problem ◽  
State Of The Art ◽  
Selection Method ◽  
Bayesian Optimization ◽  
Benchmark Problems ◽  
Multi Objective ◽  
Blackbox Optimization ◽  
Expensive Function ◽  
Area Overhead ◽  
Measure Of Uncertainty

We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto set of solutions while minimizing the number of function evaluations. For example, in hardware design optimization, we need to find the designs that trade-off performance, energy, and area overhead using expensive simulations. We propose a novel uncertainty-aware search framework referred to as USeMO to efficiently select the sequence of inputs for evaluation to solve this problem. The selection method of USeMO consists of solving a cheap MO optimization problem via surrogate models of the true functions to identify the most promising candidates and picking the best candidate based on a measure of uncertainty. We also provide theoretical analysis to characterize the efficacy of our approach. Our experiments on several synthetic and six diverse real-world benchmark problems show that USeMO consistently outperforms the state-of-the-art algorithms.

scholarly journals Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

2021 ◽  
Vol 72 ◽  
pp. 667-715
Author(s):  
Syrine Belakaria ◽  
Aryan Deshwal ◽  
Janardhan Rao Doppa
Keyword(s):  
Pareto Front ◽  
Black Box ◽  
Bayesian Optimization ◽  
Multi Objective ◽  
Expensive Function ◽  
Area Overhead ◽  
Resource Cost ◽  
Function Approximations ◽  
Total Resource ◽  
Output Space

We consider the problem of black-box multi-objective optimization (MOO) using expensive function evaluations (also referred to as experiments), where the goal is to approximate the true Pareto set of solutions by minimizing the total resource cost of experiments. For example, in hardware design optimization, we need to find the designs that trade-off performance, energy, and area overhead using expensive computational simulations. The key challenge is to select the sequence of experiments to uncover high-quality solutions using minimal resources. In this paper, we propose a general framework for solving MOO problems based on the principle of output space entropy (OSE) search: select the experiment that maximizes the information gained per unit resource cost about the true Pareto front. We appropriately instantiate the principle of OSE search to derive efficient algorithms for the following four MOO problem settings: 1) The most basic single-fidelity setting, where experiments are expensive and accurate; 2) Handling black-box constraints which cannot be evaluated without performing experiments; 3) The discrete multi-fidelity setting, where experiments can vary in the amount of resources consumed and their evaluation accuracy; and 4) The continuous-fidelity setting, where continuous function approximations result in a huge space of experiments. Experiments on diverse synthetic and real-world benchmarks show that our OSE search based algorithms improve over state-of-the-art methods in terms of both computational-efficiency and accuracy of MOO solutions.

scholarly journals Multi-Fidelity Multi-Objective Bayesian Optimization: An Output Space Entropy Search Approach

2020 ◽  
Vol 34 (06) ◽  
pp. 10035-10043 ◽  
Author(s):  
Syrine Belakaria ◽  
Aryan Deshwal ◽  
Janardhan Rao Doppa
Keyword(s):  
Bayesian Optimization ◽  
Benchmark Problems ◽  
Multi Objective Optimization ◽  
Multi Objective ◽  
Blackbox Optimization ◽  
Novel Approach ◽  
Resource Cost ◽  
System Design Optimization ◽  
Search Approach ◽  
Output Space

We study the novel problem of blackbox optimization of multiple objectives via multi-fidelity function evaluations that vary in the amount of resources consumed and their accuracy. The overall goal is to appromixate the true Pareto set of solutions by minimizing the resources consumed for function evaluations. For example, in power system design optimization, we need to find designs that trade-off cost, size, efficiency, and thermal tolerance using multi-fidelity simulators for design evaluations. In this paper, we propose a novel approach referred as Multi-Fidelity Output Space Entropy Search for Multi-objective Optimization (MF-OSEMO) to solve this problem. The key idea is to select the sequence of candidate input and fidelity-vector pairs that maximize the information gained about the true Pareto front per unit resource cost. Our experiments on several synthetic and real-world benchmark problems show that MF-OSEMO, with both approximations, significantly improves over the state-of-the-art single-fidelity algorithms for multi-objective optimization.

scholarly journals APPLICATION OF POPULATION EVOLVABILITY IN A HYPER-HEURISTIC FOR DYNAMIC MULTI-OBJECTIVE OPTIMIZATION

2019 ◽  
Vol 25 (5) ◽  
pp. 951-978 ◽  
Author(s):  
Teodoro Macias-Escobar ◽  
Laura Cruz-Reyes ◽  
Bernabé Dorronsoro ◽  
Héctor Fraire-Huacuja ◽  
Nelson Rangel-Valdez ◽  
...  
Keyword(s):  
Dynamic Optimization ◽  
Optimization Problem ◽  
Optimization Problems ◽  
Dynamic Properties ◽  
Selection Method ◽  
Multiobjective Evolutionary Algorithms ◽  
Multi Objective Optimization ◽  
Selection Methods ◽  
Dynamic Optimization Problems ◽  
Multi Objective

It is important to know the properties of an optimization problem and the difficulty an algorithm faces to solve it. Population evolvability obtains information related to both elements by analysing the probability of an algorithm to improve current solutions and the degree of those improvements. DPEM_HH is a dynamic multi-objective hyper-heuristic that uses low-level heuristic (LLH) selection methods that apply population evolvability. DPEM_HH uses dynamic multiobjective evolutionary algorithms (DMOEAs) as LLHs to solve dynamic multi-objective optimization problems (DMOPs). Population evolvability is incorporated in DPEM_HH by calculating it on each candidate DMOEA for a set of sampled generations after a change is detected, using those values to select which LLH will be applied. DPEM_HH is tested on multiple DMOPs with dynamic properties that provide several challenges. Experimental results show that DPEM_HH with a greedy LLH selection method that uses average population evolvability values can produce solutions closer to the Pareto optimal front with equal to or better diversity than previously proposed heuristics. This shows the effectiveness and feasibility of the application of population evolvability on hyperheuristics to solve dynamic optimization problems.

scholarly journals A Decision Making Approach for Multi-Objective Optimization Considering A Trade-off Method

2017 ◽  
Vol 11 (2) ◽  
pp. 178-189
Author(s):  
Tipwimol Sooktip ◽  
Naruemon Wattanapongsakorn
Keyword(s):  
Decision Maker ◽  
Optimization Problem ◽  
Benchmark Problems ◽  
Optimal Solutions ◽  
Multi Objective Optimization ◽  
Trade Off ◽  
Multi Objective ◽  
Component Allocation ◽  
Objective Value ◽  
Preferred Solutions

In multi-objective optimization problem, a set of optimal solutions is obtained from an optimization algorithm. There are many trade-off optimal solutions. However, in practice, a decision maker or user only needs one or very few solutions for implementation. Moreover, these solutions are difficult to determine from a set of optimal solutions of complex system. Therefore, a trade-off method for multi-objective optimization is proposed for identifying the preferred solutions according to the decision maker’s preference. The preference is expressed by using the trade-off between any two objectives where the decision maker is willing to worsen in one objective value in order to gain improvement in the other objective value. The trade-off method is demonstrated by using well-known two-objective and three-objective benchmark problems. Furthermore, a system design problem with component allocation is also considered to illustrate the applicability of the proposed method. The results show that the trade-off method can be applied for solving practical problems to identify the final solution(s) and easy to use even when the decision maker lacks some knowledge or not an expert in the problem solving. The decision maker only gives his/her preference information.  Then, the corresponding optimal solutions will be obtained, accordingly.

A Novel Multi-Objective Competitive Swarm Optimization Algorithm

2020 ◽  
Vol 11 (4) ◽  
pp. 114-129
Author(s):  
Prabhujit Mohapatra ◽  
Kedar Nath Das ◽  
Santanu Roy ◽  
Ram Kumar ◽  
Nilanjan Dey
Keyword(s):  
Optimization Algorithm ◽  
State Of The Art ◽  
Statistical Tests ◽  
The Other ◽  
Benchmark Problems ◽  
Dominance Relationship ◽  
Nsga Ii ◽  
Swarm Optimization ◽  
Multi Objective ◽  
External Archive

In this article, a new algorithm, namely the multi-objective competitive swarm optimizer (MOCSO), is introduced to handle multi-objective problems. The algorithm has been principally motivated from the competitive swarm optimizer (CSO) and the NSGA-II algorithm. In MOCSO, a pair wise competitive scenario is presented to achieve the dominance relationship between two particles in the population. In each pair wise competition, the particle that dominates the other particle is considered the winner and the other is consigned as the loser. The loser particles learn from the respective winner particles in each individual competition. The inspired CSO algorithm does not use any memory to remember the global best or personal best particles, hence, MOCSO does not need any external archive to store elite particles. The experimental results and statistical tests confirm the superiority of MOCSO over several state-of-the-art multi-objective algorithms in solving benchmark problems.

scholarly journals An Entropy-Based Multiobjective Evolutionary Algorithm with an Enhanced Elite Mechanism

2012 ◽  
Vol 2012 ◽  
pp. 1-11 ◽  
Author(s):  
Yufang Qin ◽  
Junzhong Ji ◽  
Chunnian Liu
Keyword(s):  
Evolutionary Algorithm ◽  
Pareto Front ◽  
Optimization Problem ◽  
State Of The Art ◽  
Early Stage ◽  
Test Problems ◽  
Multiobjective Optimization Problem ◽  
Multi Objective Optimization ◽  
Nsga Ii ◽  
Multi Objective

Multiobjective optimization problem (MOP) is an important and challenging topic in the fields of industrial design and scientific research. Multi-objective evolutionary algorithm (MOEA) has proved to be one of the most efficient algorithms solving the multi-objective optimization. In this paper, we propose an entropy-based multi-objective evolutionary algorithm with an enhanced elite mechanism (E-MOEA), which improves the convergence and diversity of solution set in MOPs effectively. In this algorithm, an enhanced elite mechanism is applied to guide the direction of the evolution of the population. Specifically, it accelerates the population to approach the true Pareto front at the early stage of the evolution process. A strategy based on entropy is used to maintain the diversity of population when the population is near to the Pareto front. The proposed algorithm is executed on widely used test problems, and the simulated results show that the algorithm has better or comparative performances in convergence and diversity of solutions compared with two state-of-the-art evolutionary algorithms: NSGA-II, SPEA2 and the MOSADE.

scholarly journals Intelligent Online Path Planning for UAVs in Adversarial Environments

10.5772/45604 ◽  
2012 ◽  
Vol 9 (1) ◽  
pp. 3 ◽  
Author(s):  
Xingguang Peng ◽  
Demin Xu
Keyword(s):  
Path Planning ◽  
Predictive Control ◽  
Optimization Problem ◽  
Benchmark Problems ◽  
Multi Objective ◽  
Pareto Sets ◽  
Basic Issue ◽  
Solution Selection ◽  
Path Planner ◽  
Adversarial Environments

Online path planning (OPP) for unmanned aerial vehicles (UAVs) is a basic issue of intelligent flight and is indeed a dynamic multi-objective optimization problem (DMOP). In this paper, an OPP framework is proposed in the sense of model predictive control (MPC) to continuously update the environmental information for the planner. For solving the DMOP involved in the MPC we propose a dynamic multi-objective evolutionary algorithm based on linkage and prediction (LP-DMOEA). Within this algorithm, the historical Pareto sets are collected and analysed to enhance the performance. For intelligently selecting the best path from the output of the OPP, the Bayesian network and fuzzy logic are used to quantify the bias to each optimization objective. The DMOEA is validated on three benchmark problems characterized by different changing types in decision and objective spaces. Moreover, the simulation results show that the LP-DMOEA overcomes the restart method for OPP. The decision-making method for solution selection can assess the situation in an adversarial environment and accordingly adapt the path planner.

scholarly journals Balancing Exploration and Exploitation With Decomposition-Based Dynamic Multi-Objective Evolutionary Algorithm

2021 ◽  
Vol 15 (4) ◽  
pp. 1-23
Author(s):  
Qing Zhang ◽  
Ruwang Jiao ◽  
Sanyou Zeng ◽  
Zhigao Zeng
Keyword(s):  
Global Optimization ◽  
Evolutionary Algorithm ◽  
Optimization Problem ◽  
Optimization Problems ◽  
Early Stage ◽  
Population Diversity ◽  
Benchmark Problems ◽  
Exploration And Exploitation ◽  
Multi Objective ◽  
Count Function

Balancing exploration and exploitation is a crucial issue in evolutionary global optimization. This paper proposes a decomposition-based dynamic multi-objective evolutionary algorithm for addressing global optimization problems. In the proposed method, the niche count function is regarded as a helper objective to maintain the population diversity, which converts a global optimization problem to a multi-objective optimization problem (MOP). The niche-count value is controlled by the niche radius. In the early stage of evolution, a large niche radius promotes the population diversity for better exploration; in the later stage of evolution, a niche radius close to 0 focuses on convergence for better exploitation. Through the whole evolution process, the niche radius is dynamically decreased from a large value to zero, which can provide a sound balance between the exploration and exploitation. Experimental results on CEC 2014 benchmark problems reveal that the proposed algorithm is capable of offering high-quality solutions, in comparison with four state-of-the-art algorithms.

scholarly journals Occupancy map building through Bayesian exploration

2019 ◽  
Vol 38 (7) ◽  
pp. 769-792 ◽  
Author(s):  
Gilad Francis ◽  
Lionel Ott ◽  
Roman Marchant ◽  
Fabio Ramos
Keyword(s):  
State Of The Art ◽  
Holistic Approach ◽  
Bayesian Optimization ◽  
Map Building ◽  
Forward Simulation ◽  
Expensive Function ◽  
Safety Constraints ◽  
Series Of Experiments ◽  
Consistent Performance ◽  
Better Than

We propose a novel holistic approach to safe autonomous exploration and map building based on constrained Bayesian optimization. This method finds optimal continuous paths instead of discrete sensing locations that inherently satisfy motion and safety constraints. Evaluating both the objective and constraints functions requires forward simulation of expected observations. As such, evaluations are costly, and therefore the Bayesian optimizer proposes only paths that are likely to yield optimal results and satisfy the constraints with high confidence. By balancing the reward and risk associated with each path, the optimizer minimizes the number of expensive function evaluations. We demonstrate the effectiveness of our approach in a series of experiments both in simulation and with a real ground robot and provide comparisons with other exploration techniques. The experimental results show that our method provides robust and consistent performance in all tests and performs better than or as good as the state of the art.

scholarly journals Identification of Essential Proteins using a Novel Multi-objective Optimization Method

2020 ◽  
Author(s):  
Chong Wu ◽  
Houwang Zhang ◽  
Le Zhang ◽  
Hanying Zheng
Keyword(s):  
Protein Interactions ◽  
Optimization Problem ◽  
State Of The Art ◽  
Optimization Method ◽  
Multi Objective Optimization ◽  
Protein Protein Interactions ◽  
Generalization Ability ◽  
Essential Proteins ◽  
Multi Objective ◽  
Voting Strategy

<p>Using graph theory to identify essential proteins is a hot topic at present. These methods are called network-based methods. However, the generalization ability of most network-based methods is not satisfactory. Hence, in this paper, we consider the identification of essential proteins as a multi-objective optimization problem and use a novel multi-objective optimization method to solve it. The optimization result is a set of Pareto solutions. Every solution in this set is a vector which has a certain number of essential protein candidates and is considered as an independent predictor or voter. We use a voting strategy to assemble the results of these predictors. To validate our method, we apply it on the protein-protein interactions (PPI) datasets of two species (Yeast and Escherichia coli). The experiment results show that our method outperforms state-of-the-art methods in terms of sensitive, specificity, F-measure, accuracy, and generalization ability.</p>

Sign in / Sign up

Export Citation Format

Share Document