Filters








15,487 Hits in 4.9 sec

PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures

Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun
2018 International Conference on Learning Representations  
., inference time and power consumptions) that can be critical for portable devices with limited computing resources.  ...  We propose PPP-Net: a multi-objective architectural search framework to automatically generate networks that achieve Pareto Optimality.  ...  APPROACH We propose Platform-aware Progressive search for Pareto-optimal Net (PPP-Net) -a framework automatically generates neural networks with a predefined number of replicated blocks.  ... 
dblp:conf/iclr/DongCJWS18 fatcat:qnwovbce4fdxrjw2gruhevtc74

DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures [article]

Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun
2018 arXiv   pre-print
We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., inference time and memory usage) and device-agnostic (e.g., accuracy  ...  Optimizing neural architecture for device-related objectives is immensely crucial for deploying deep networks on portable devices with limited computing resources.  ...  Acknowledgement We are grateful to the National Center for High-performance Computing for computer time and facilities, and Google Research, MediaTek, MOST 107-2634-F-007-007 for their support.  ... 
arXiv:1806.08198v2 fatcat:w2okcidp7nattmtgyphrg2vf3e

Age-Fitness Pareto Optimization [chapter]

Michael Schmidt, Hod Lipson
2010 Genetic Programming Theory and Practice VIII  
Here, we propose that treating age as an explicit optimization criterion can increase performance even further, with fewer algorithm implementation parameters.  ...  We propose a multi-objective method for avoiding premature convergence in evolutionary algorithms, and demonstrate a threefold performance improvement over comparable methods.  ...  Expending additional computational effort in the evolution often fails to make any substantial progress. This problem is known as premature convergence [1, 2] .  ... 
doi:10.1007/978-1-4419-7747-2_8 fatcat:gl3ld2ync5fe3basoemp6fpswi

DPP-Net: Device-Aware Progressive Search for Pareto-Optimal Neural Architectures [chapter]

Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun
2018 Lecture Notes in Computer Science  
We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., inference time and memory usage) and device-agnostic (e.g., accuracy  ...  Optimizing neural architecture for devicerelated objectives is immensely crucial for deploying deep networks on portable devices with limited computing resources.  ...  Acknowledgement We are grateful to the National Center for High-performance Computing for computer time and facilities, and Google Research, MediaTek, MOST 107-2634-F-007-007 for their support.  ... 
doi:10.1007/978-3-030-01252-6_32 fatcat:ff45jydddjbc3puknmo7r4qghy

Identification of Cancer–associated metabolic vulnerabilities by modeling multi-objective optimality in metabolism

Ziwei Dai, Shiyu Yang, Liyan Xu, Hongrong Hu, Kun Liao, Jianghuang Wang, Qian Wang, Shuaishi Gao, Bo Li, Luhua Lai
2019 Cell Communication and Signaling  
Computational modeling of genome-scale metabolic models is an effective approach for designing new therapeutics targeting dysregulated cancer metabolism by identifying metabolic enzymes crucial for satisfying  ...  It is thus necessary to develop computational models covering multiple metabolic objectives to study cancer metabolism and identify novel metabolic targets.  ...  Ning Yin for helpful discussions and insightful comments on the manuscript and Dr. Chunmei Li for help with the cancer cell lines.  ... 
doi:10.1186/s12964-019-0439-y pmid:31601242 pmcid:PMC6785927 fatcat:sazszlollzfthak255y66lnfwu

Evolutionary Computation for Large-scale Multi-objective Optimization: A Decade of Progresses

Wen-Jing Hong, Peng Yang, Ke Tang
2021 International Journal of Automation and Computing  
This paper reviews the progress of evolutionary computation for large-scale multi-objective optimization from two angles.  ...  While evolutionary algorithms (EAs) have been widely acknowledged as a mainstream method for MOPs, most research progress and successful applications of EAs have been restricted to MOPs with small-scale  ...  Conclusions and future directions In this paper, the evolutionary computation for largescale multi-objective optimization during the past decade of progress is reviewed.  ... 
doi:10.1007/s11633-020-1253-0 fatcat:q636cuvarbco7kmnvthnfysa54

Challenges in Automatic Optimization of Arithmetic Circuits

Ajay K. Verma, Philip Brisk, Paolo Ienne
2009 2009 19th IEEE Symposium on Computer Arithmetic  
Despite the impressive progress of logic synthesis in the past decade, finding the best architecture for a given circuit still remains an open and largely unsolved problem, especially for arithmetic circuits  ...  Progress has clearly been made, but much further work is still needed to narrow the gap between the effectiveness of logic synthesis techniques for arithmetic and control-oriented circuits.  ...  Progressive Decomposition repeatedly selects a group of input bits to optimize, based on an appropriate metric.  ... 
doi:10.1109/arith.2009.39 dblp:conf/arith/VermaBI09 fatcat:4sisytdg5vddhjekcurcb4pdfq

A simulation–optimization strategy to deal simultaneously with tens of decision variables and multiple performance measures in manufacturing

Esmeralda Niño-Pérez, Yaileen M. Méndez-Vázquez, Dick E. Arias-González, Mauricio Cabrera-Ríos
2017 Journal of Simulation  
This work addresses the multiple criteria simulation optimization problem.  ...  The results show a rapid convergence to a more precise characterization of the Pareto-efficient solutions.  ...  The first idea related to manufacturing simulation-optimization in our group is presented in (Cabrera-Ríos, Mount-Campbell, and Irani 2002a) , where the design of a manufacturing cell was approached through  ... 
doi:10.1057/s41273-017-0056-y fatcat:iy4tl36aaretvhz42jjjfaftc4

Molecular Optimization Using Computational Multi-Objective Methods

C.A. Nicolaou, N. Brown, C.S. Pattichis
2007 Zenodo  
Multi-objective optimization (MOOP) methods introduce a new approach for gaining optimality based on compromises and trade-offs among the various objectives.  ...  This approach, known as single-objective optimization (SOOP), strives to discover a single optimal solution to the optimization problem.  ...  Several additional research groups are active in the field of Pareto-based docking optimization applications.  ... 
doi:10.5281/zenodo.2555799 fatcat:r4d75kodwjatppw2z4yohbdsva

Identifying Best-Fitting Inputs in Health-Economic Model Calibration

Eva A. Enns, Lauren E. Cipriano, Cyrena T. Simons, Chung Yin Kong
2014 Medical decision making  
We present an alternative approach to identifying best-fitting input sets based on the concept of Pareto-optimality.  ...  The Pareto frontier approach eliminates the need to make these choices by  ...  Acknowledgments Financial support for this study was provided in part by the National Cancer Institute (K25CA133141).  ... 
doi:10.1177/0272989x14528382 pmid:24799456 pmcid:PMC4277724 fatcat:oaopwynl5bbpzbgy2hxd5d4554

Multi-objective optimization of production scheduling with evolutionary computation: A review

Robert Ojstersek, Miran Brezocnik, Borut Buchmeister
2020 International Journal of Industrial Engineering Computations  
Using the citation analysis of the scientific publications, the application for the MO optimization in manufacturing scheduling is discussed.  ...  The research field of EC methods is presented, then EC algorithms' classification is introduced for the purpose of production scheduling optimization.  ...  For these functions, there is an unlimited number of Pareto optimal solutions (Deb et al., 2000) . Pareto solutions are non-dominated, Pareto optimal, Pareto effective (Deb & Jain, 2014) .  ... 
doi:10.5267/j.ijiec.2020.1.003 fatcat:qw6qauvkvzg4zjsfvxtviiincq

A parallel exact hybrid approach for solving multi-objective problems on the computational grid

M. Mezmaz, N. Melab, E.-G. Talbi
2006 Proceedings 20th IEEE International Parallel & Distributed Processing Symposium  
Such approach profits from both the exploration power of the GA, the intensification capability of the MA and the ability of the B&B to provide optimal solutions with proof of optimality.  ...  To fully exploit the resources of a computational grid, the hybrid method is parallelized according to three wellknown parallel models -the island model for the GA, the multi-start model for the MA and  ...  The set of optimal solutions is called Pareto Optimal Set, and the Pareto front is the corresponding set of the Pareto Optimal Set in the objective space.  ... 
doi:10.1109/ipdps.2006.1639525 dblp:conf/ipps/MezmazMT06 fatcat:vfeeh6zqozffpbv7lbj57mejw4

Agent assisted interactive algorithm for computationally demanding multiobjective optimization problems

Vesa Ojalehto, Dmitry Podkopaev, Kaisa Miettinen
2015 Computers and Chemical Engineering  
Agent assisted interactive algorithm for computationally demanding multiobjective optimization problems.  ...  Agent assisted interactive algorithm for computationally demanding multiobjective optimization problems Ojalehto, Vesa; Podkopaev, Dmitry; Miettinen, Kaisa Ojalehto, V., Podkopaev, D., & Miettinen, K.  ...  .), Multiobjective Optimization: Interactive and Evolutionary Approaches, Springer-Verlag, 2008. [2] K. Miettinen, Nonlinear Multiobjective Optimization, Kluwer Academic Publishers, 1999.  ... 
doi:10.1016/j.compchemeng.2015.03.004 fatcat:qjqp2yt6bvampkkwn32cbza7lu

Bottom-up approaches to achieve Pareto optimal agreements in group decision making

Victor Sanchez-Anguix, Reyhan Aydoğan, Tim Baarslag, Catholijn Jonker
2019 Knowledge and Information Systems  
First, we prove that an outcome that is Pareto optimal for subgroups is also Pareto optimal for the group as a whole.  ...  In this article, we introduce a new paradigm to achieve Pareto optimality in group decisionmaking processes: bottom-up approaches to Pareto optimality.  ...  We would like to thank the anonymous reviewers for their useful comments.  ... 
doi:10.1007/s10115-018-01325-y fatcat:64ozwytjszgm3mks4luplgcmde

Multi-Objective Optimization Methods as a Decision Making Strategy

Muhammad Nagy, Yasser Mansour, Sherif Abdelmohsen, Ain Shams University
2020 International Journal of Engineering Research and  
To overcome this limitation, multi-objective optimization (MOO) becomes one of the recent optimization approaches to formulate decision making problems in a more realistic manner.  ...  One of the most basic concepts in humankind's life is the search for an optimal state. As long as the life continues, seeking for perfection in decision making of many areas is fundamental.  ...  Strict Pareto Optimality A solution is strictly Pareto-optimal if there is no such that for . G.  ... 
doi:10.17577/ijertv9is030480 fatcat:hwhkcvnqfnfubhz7f6dsgrnhaa
« Previous Showing results 1 — 15 out of 15,487 results