SlideShare ist ein Scribd-Unternehmen logo
1 von 22
Comparison-Based Complexity
of Multi-Objective Optimization


                    Paper by O. Teytaud
         Presented by M. Schoenauer
      TAO, Inria, Lri, UMR CNRS 8623,
                    Université Paris-Sud
Outline
Multiobjective optimization

Complexity upper bounds

Complexity lower bounds

Discussion
Evolutionary multi-objective
optimization
 Generate a population
 Evaluate fitness values
 Select the « best » (various rules are possible
  here)
 Generate offspring
 Go back to the Evaluation step.
Model of fitness functions ?
No assumption ?
  Unrealistically pessimistic results
  Unreadable lower bounds



Let's do as in:
                                         ==> quadratic
                                        convex objective
                                           functions
Outline
Multiobjective optimization

Complexity upper bounds

Complexity lower bounds

Discussion
Complexity upper bounds
Each objective function = a sphere
Below just a short overview of algorithms;
 ==> the real algorithms are a bit more
 tricky
For finding the whole Pareto front :
  Optimize each objective separately
  The PF is the convex hull
For finding a single point :
  Optimize any single objective
Finding one point of the Pareto Set

d objective functions
In dimension N
One point at distance at most e of the PF
cost=O( (N+1-d) log (1/e) )
Proof : M log(1/e) in monoobjective
  optimization where M is the codimension
  of the set of optima (Gelly Teytaud, 2006)
Finding the whole Pareto Set
d objective functions
In dimension N
One point at distance at most e of the PF for
  the Hausdorff metric
cost=O( (Nd) log (1/e) )
Proof : d times the monoobjective case.
Outline
Multiobjective optimization

Complexity upper bounds

Complexity lower bounds
  Proof technique (monoobjective)
  The MO case
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           10
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           11
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           12
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           13
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           14
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           15
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           16
We want to know how many iterations we need for reaching precision 
  in an evolutionary algorithm.

Key observation: (most) evolutionary algorithms are comparison-based

Let's consider (for simplicity) a deterministic selection-based non-elitist
 algorithm

First idea: how many different branches we have in a run ?
   We select  points among 
   Therefore, at most K = ! / ( ! (  -  )!) different branches

Second idea: how many different answers should we able to give ?
   Use packing numbers: at least N() different possible answers

Conclusion: the number n of iterations should verify
                  Kn ≥ N (  )

Frédéric Lemoine                 MIG 11/07/2008                           17
Outline
Multiobjective optimization

Complexity upper bounds

Complexity lower bounds
  Proof technique (monoobjective)
  The MO case
How to apply this in MOO ?
Covering numbers can be computed also for
  Hausdorff distance ==>
Plus a little bit of boring maths
Leads to bounds as expected
  Nd log(1/e) for the whole Pareto set (Hausdorff)
  (N+1-d) log(1/e) for pointwise convergence (distance to
    one point of the Pareto set)
                            N=dimension, d=nb of objectives
Results in multiobjective cases
The proof method is not new
          (Fournier & Teytaud, Algorithmica 2010)


Its application to MOO is new :
  Tight bounds
  But no result in case of use of surrogate models
    (as for corresponding results in the
    monoobjective case) ; in fact, the problem
    becomes unrealistically easy with surrogate
    models...
Outline
Multiobjective optimization

Complexity upper bounds

Complexity lower bounds

Discussion
Sorry for not being here
                                  ==> really impossible
Discussion                        ==> all email questions welcome



Tight bounds thanks to a realistic model
Combining previous papers



           Complexity bounds               Relevant model

Maybe an extension : using VC-dimension
This paper did it
(single objective)

Weitere ähnliche Inhalte

Was ist angesagt?

A Connectionist approach to Part-Of-Speech Tagging
A Connectionist approach to Part-Of-Speech TaggingA Connectionist approach to Part-Of-Speech Tagging
A Connectionist approach to Part-Of-Speech TaggingFrancisco Zamora-Martinez
 
International Journal of Computational Engineering Research(IJCER)
 International Journal of Computational Engineering Research(IJCER)  International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER) ijceronline
 
Probabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible WorldsProbabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible WorldsFulvio Rotella
 
Self Stabilizing Depth-first Search
Self Stabilizing Depth-first SearchSelf Stabilizing Depth-first Search
Self Stabilizing Depth-first SearchIntan Dzikria
 
Data Complexity in EL Family of Description Logics
Data Complexity in EL Family of Description LogicsData Complexity in EL Family of Description Logics
Data Complexity in EL Family of Description LogicsAdila Krisnadhi
 
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...Simplilearn
 
ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text ijnlc
 
CommunicationComplexity1_jieren
CommunicationComplexity1_jierenCommunicationComplexity1_jieren
CommunicationComplexity1_jierenjie ren
 
Graph Neural Network in practice
Graph Neural Network in practiceGraph Neural Network in practice
Graph Neural Network in practicetuxette
 
ON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMS
ON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMSON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMS
ON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMScscpconf
 
A probabilistic data encryption scheme (pdes)
A probabilistic data encryption scheme (pdes)A probabilistic data encryption scheme (pdes)
A probabilistic data encryption scheme (pdes)Alexander Decker
 
(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...
(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...
(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...Masahiro Suzuki
 
Introduction to theory of computation
Introduction to theory of computationIntroduction to theory of computation
Introduction to theory of computationVinod Tyagi
 
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXTGENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXTcscpconf
 

Was ist angesagt? (20)

A Connectionist approach to Part-Of-Speech Tagging
A Connectionist approach to Part-Of-Speech TaggingA Connectionist approach to Part-Of-Speech Tagging
A Connectionist approach to Part-Of-Speech Tagging
 
Daa chapter 1
Daa chapter 1Daa chapter 1
Daa chapter 1
 
Mm2521542158
Mm2521542158Mm2521542158
Mm2521542158
 
International Journal of Computational Engineering Research(IJCER)
 International Journal of Computational Engineering Research(IJCER)  International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Probabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible WorldsProbabilistic Abductive Logic Programming using Possible Worlds
Probabilistic Abductive Logic Programming using Possible Worlds
 
Bq25399403
Bq25399403Bq25399403
Bq25399403
 
Self Stabilizing Depth-first Search
Self Stabilizing Depth-first SearchSelf Stabilizing Depth-first Search
Self Stabilizing Depth-first Search
 
Data Complexity in EL Family of Description Logics
Data Complexity in EL Family of Description LogicsData Complexity in EL Family of Description Logics
Data Complexity in EL Family of Description Logics
 
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...
TensorFlow Tutorial | Deep Learning With TensorFlow | TensorFlow Tutorial For...
 
Iclr2016 vaeまとめ
Iclr2016 vaeまとめIclr2016 vaeまとめ
Iclr2016 vaeまとめ
 
ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text ANN Based POS Tagging For Nepali Text
ANN Based POS Tagging For Nepali Text
 
CommunicationComplexity1_jieren
CommunicationComplexity1_jierenCommunicationComplexity1_jieren
CommunicationComplexity1_jieren
 
ARIC Team Seminar
ARIC Team SeminarARIC Team Seminar
ARIC Team Seminar
 
Compositional Program Analysis using Max-SMT
Compositional Program Analysis using Max-SMTCompositional Program Analysis using Max-SMT
Compositional Program Analysis using Max-SMT
 
Graph Neural Network in practice
Graph Neural Network in practiceGraph Neural Network in practice
Graph Neural Network in practice
 
ON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMS
ON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMSON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMS
ON THE DUALITY FEATURE OF P-CLASS PROBLEMS AND NP COMPLETE PROBLEMS
 
A probabilistic data encryption scheme (pdes)
A probabilistic data encryption scheme (pdes)A probabilistic data encryption scheme (pdes)
A probabilistic data encryption scheme (pdes)
 
(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...
(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...
(DL hacks輪読) How to Train Deep Variational Autoencoders and Probabilistic Lad...
 
Introduction to theory of computation
Introduction to theory of computationIntroduction to theory of computation
Introduction to theory of computation
 
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXTGENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
GENERAL REGRESSION NEURAL NETWORK BASED POS TAGGING FOR NEPALI TEXT
 

Andere mochten auch

Why power system studies (and many others!) should be open data / open source
Why power system studies (and many others!) should be open data / open sourceWhy power system studies (and many others!) should be open data / open source
Why power system studies (and many others!) should be open data / open sourceOlivier Teytaud
 
Derivative Free Optimization
Derivative Free OptimizationDerivative Free Optimization
Derivative Free OptimizationOlivier Teytaud
 
Undecidability in partially observable deterministic games
Undecidability in partially observable deterministic gamesUndecidability in partially observable deterministic games
Undecidability in partially observable deterministic gamesOlivier Teytaud
 
Presentación1 1
Presentación1 1Presentación1 1
Presentación1 1Jhavi17
 
France presented to Taiwanese people
France presented to Taiwanese peopleFrance presented to Taiwanese people
France presented to Taiwanese peopleOlivier Teytaud
 
Machine learning 2016: deep networks and Monte Carlo Tree Search
Machine learning 2016: deep networks and Monte Carlo Tree SearchMachine learning 2016: deep networks and Monte Carlo Tree Search
Machine learning 2016: deep networks and Monte Carlo Tree SearchOlivier Teytaud
 
reinforcement learning for difficult settings
reinforcement learning for difficult settingsreinforcement learning for difficult settings
reinforcement learning for difficult settingsOlivier Teytaud
 
Derandomized evolution strategies (quasi-random)
Derandomized evolution strategies (quasi-random)Derandomized evolution strategies (quasi-random)
Derandomized evolution strategies (quasi-random)Olivier Teytaud
 

Andere mochten auch (11)

Why power system studies (and many others!) should be open data / open source
Why power system studies (and many others!) should be open data / open sourceWhy power system studies (and many others!) should be open data / open source
Why power system studies (and many others!) should be open data / open source
 
Derivative Free Optimization
Derivative Free OptimizationDerivative Free Optimization
Derivative Free Optimization
 
Undecidability in partially observable deterministic games
Undecidability in partially observable deterministic gamesUndecidability in partially observable deterministic games
Undecidability in partially observable deterministic games
 
Plantilla trazos
Plantilla trazosPlantilla trazos
Plantilla trazos
 
An introduction to SVN
An introduction to SVNAn introduction to SVN
An introduction to SVN
 
Presentación1 1
Presentación1 1Presentación1 1
Presentación1 1
 
Batchal slides
Batchal slidesBatchal slides
Batchal slides
 
France presented to Taiwanese people
France presented to Taiwanese peopleFrance presented to Taiwanese people
France presented to Taiwanese people
 
Machine learning 2016: deep networks and Monte Carlo Tree Search
Machine learning 2016: deep networks and Monte Carlo Tree SearchMachine learning 2016: deep networks and Monte Carlo Tree Search
Machine learning 2016: deep networks and Monte Carlo Tree Search
 
reinforcement learning for difficult settings
reinforcement learning for difficult settingsreinforcement learning for difficult settings
reinforcement learning for difficult settings
 
Derandomized evolution strategies (quasi-random)
Derandomized evolution strategies (quasi-random)Derandomized evolution strategies (quasi-random)
Derandomized evolution strategies (quasi-random)
 

Ähnlich wie Complexity of multiobjective optimization

17- Kernels and Clustering.pptx
17- Kernels and Clustering.pptx17- Kernels and Clustering.pptx
17- Kernels and Clustering.pptxssuser2023c6
 
Design and Analysis of Algorithm Brute Force 1.ppt
Design and Analysis of Algorithm Brute Force 1.pptDesign and Analysis of Algorithm Brute Force 1.ppt
Design and Analysis of Algorithm Brute Force 1.pptmoiza354
 
Java and Deep Learning (Introduction)
Java and Deep Learning (Introduction)Java and Deep Learning (Introduction)
Java and Deep Learning (Introduction)Oswald Campesato
 
Algorithm chapter 1
Algorithm chapter 1Algorithm chapter 1
Algorithm chapter 1chidabdu
 
Machine learning and Neural Networks
Machine learning and Neural NetworksMachine learning and Neural Networks
Machine learning and Neural Networksbutest
 
Basic Computer Engineering Unit II as per RGPV Syllabus
Basic Computer Engineering Unit II as per RGPV SyllabusBasic Computer Engineering Unit II as per RGPV Syllabus
Basic Computer Engineering Unit II as per RGPV SyllabusNANDINI SHARMA
 
01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms NotesAndres Mendez-Vazquez
 
CMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docx
CMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docxCMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docx
CMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docxmonicafrancis71118
 
[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare Events[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare EventsTaegyun Jeon
 
Machine Learning and Artificial Neural Networks.ppt
Machine Learning and Artificial Neural Networks.pptMachine Learning and Artificial Neural Networks.ppt
Machine Learning and Artificial Neural Networks.pptAnshika865276
 
Parallel Computing 2007: Bring your own parallel application
Parallel Computing 2007: Bring your own parallel applicationParallel Computing 2007: Bring your own parallel application
Parallel Computing 2007: Bring your own parallel applicationGeoffrey Fox
 
Data Structures- Part1 overview and review
Data Structures- Part1 overview and reviewData Structures- Part1 overview and review
Data Structures- Part1 overview and reviewAbdullah Al-hazmy
 
Initialization methods for the tsp with time windows using variable neighborh...
Initialization methods for the tsp with time windows using variable neighborh...Initialization methods for the tsp with time windows using variable neighborh...
Initialization methods for the tsp with time windows using variable neighborh...Konstantinos Giannakis
 
Aad introduction
Aad introductionAad introduction
Aad introductionMr SMAK
 

Ähnlich wie Complexity of multiobjective optimization (20)

17- Kernels and Clustering.pptx
17- Kernels and Clustering.pptx17- Kernels and Clustering.pptx
17- Kernels and Clustering.pptx
 
Design and Analysis of Algorithm Brute Force 1.ppt
Design and Analysis of Algorithm Brute Force 1.pptDesign and Analysis of Algorithm Brute Force 1.ppt
Design and Analysis of Algorithm Brute Force 1.ppt
 
tutorial.ppt
tutorial.ppttutorial.ppt
tutorial.ppt
 
Java and Deep Learning (Introduction)
Java and Deep Learning (Introduction)Java and Deep Learning (Introduction)
Java and Deep Learning (Introduction)
 
Algorithm chapter 1
Algorithm chapter 1Algorithm chapter 1
Algorithm chapter 1
 
Machine learning and Neural Networks
Machine learning and Neural NetworksMachine learning and Neural Networks
Machine learning and Neural Networks
 
Ch10 Recursion
Ch10 RecursionCh10 Recursion
Ch10 Recursion
 
Cwkaa 2010
Cwkaa 2010Cwkaa 2010
Cwkaa 2010
 
Basic Computer Engineering Unit II as per RGPV Syllabus
Basic Computer Engineering Unit II as per RGPV SyllabusBasic Computer Engineering Unit II as per RGPV Syllabus
Basic Computer Engineering Unit II as per RGPV Syllabus
 
Daa
DaaDaa
Daa
 
01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes01 Notes Introduction Analysis of Algorithms Notes
01 Notes Introduction Analysis of Algorithms Notes
 
CMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docx
CMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docxCMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docx
CMIS 102 Hands-On Lab Week 4OverviewThis hands-on lab all.docx
 
[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare Events[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare Events
 
Machine Learning and Artificial Neural Networks.ppt
Machine Learning and Artificial Neural Networks.pptMachine Learning and Artificial Neural Networks.ppt
Machine Learning and Artificial Neural Networks.ppt
 
Parallel Computing 2007: Bring your own parallel application
Parallel Computing 2007: Bring your own parallel applicationParallel Computing 2007: Bring your own parallel application
Parallel Computing 2007: Bring your own parallel application
 
Data Structures- Part1 overview and review
Data Structures- Part1 overview and reviewData Structures- Part1 overview and review
Data Structures- Part1 overview and review
 
01-algo.ppt
01-algo.ppt01-algo.ppt
01-algo.ppt
 
Initialization methods for the tsp with time windows using variable neighborh...
Initialization methods for the tsp with time windows using variable neighborh...Initialization methods for the tsp with time windows using variable neighborh...
Initialization methods for the tsp with time windows using variable neighborh...
 
nnml.ppt
nnml.pptnnml.ppt
nnml.ppt
 
Aad introduction
Aad introductionAad introduction
Aad introduction
 

Kürzlich hochgeladen

presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Zilliz
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Victor Rentea
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 

Kürzlich hochgeladen (20)

presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 

Complexity of multiobjective optimization

  • 1. Comparison-Based Complexity of Multi-Objective Optimization Paper by O. Teytaud Presented by M. Schoenauer TAO, Inria, Lri, UMR CNRS 8623, Université Paris-Sud
  • 2. Outline Multiobjective optimization Complexity upper bounds Complexity lower bounds Discussion
  • 3. Evolutionary multi-objective optimization Generate a population Evaluate fitness values Select the « best » (various rules are possible here) Generate offspring Go back to the Evaluation step.
  • 4. Model of fitness functions ? No assumption ? Unrealistically pessimistic results Unreadable lower bounds Let's do as in: ==> quadratic convex objective functions
  • 5. Outline Multiobjective optimization Complexity upper bounds Complexity lower bounds Discussion
  • 6. Complexity upper bounds Each objective function = a sphere Below just a short overview of algorithms; ==> the real algorithms are a bit more tricky For finding the whole Pareto front : Optimize each objective separately The PF is the convex hull For finding a single point : Optimize any single objective
  • 7. Finding one point of the Pareto Set d objective functions In dimension N One point at distance at most e of the PF cost=O( (N+1-d) log (1/e) ) Proof : M log(1/e) in monoobjective optimization where M is the codimension of the set of optima (Gelly Teytaud, 2006)
  • 8. Finding the whole Pareto Set d objective functions In dimension N One point at distance at most e of the PF for the Hausdorff metric cost=O( (Nd) log (1/e) ) Proof : d times the monoobjective case.
  • 9. Outline Multiobjective optimization Complexity upper bounds Complexity lower bounds Proof technique (monoobjective) The MO case
  • 10. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 10
  • 11. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 11
  • 12. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 12
  • 13. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 13
  • 14. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 14
  • 15. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 15
  • 16. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 16
  • 17. We want to know how many iterations we need for reaching precision  in an evolutionary algorithm. Key observation: (most) evolutionary algorithms are comparison-based Let's consider (for simplicity) a deterministic selection-based non-elitist algorithm First idea: how many different branches we have in a run ? We select  points among  Therefore, at most K = ! / ( ! (  -  )!) different branches Second idea: how many different answers should we able to give ? Use packing numbers: at least N() different possible answers Conclusion: the number n of iterations should verify Kn ≥ N (  ) Frédéric Lemoine MIG 11/07/2008 17
  • 18. Outline Multiobjective optimization Complexity upper bounds Complexity lower bounds Proof technique (monoobjective) The MO case
  • 19. How to apply this in MOO ? Covering numbers can be computed also for Hausdorff distance ==> Plus a little bit of boring maths Leads to bounds as expected Nd log(1/e) for the whole Pareto set (Hausdorff) (N+1-d) log(1/e) for pointwise convergence (distance to one point of the Pareto set) N=dimension, d=nb of objectives
  • 20. Results in multiobjective cases The proof method is not new (Fournier & Teytaud, Algorithmica 2010) Its application to MOO is new : Tight bounds But no result in case of use of surrogate models (as for corresponding results in the monoobjective case) ; in fact, the problem becomes unrealistically easy with surrogate models...
  • 21. Outline Multiobjective optimization Complexity upper bounds Complexity lower bounds Discussion
  • 22. Sorry for not being here ==> really impossible Discussion ==> all email questions welcome Tight bounds thanks to a realistic model Combining previous papers Complexity bounds Relevant model Maybe an extension : using VC-dimension This paper did it (single objective)