SlideShare ist ein Scribd-Unternehmen logo
1 von 29
Downloaden Sie, um offline zu lesen
Simplified Runtime Analysis of
Estimation of Distribution Algorithms
Duc-Cuong Dang Per Kristian Lehre
University of Nottingham
United Kingdom
Madrid, Spain
July, 11-15th 2015
Outline
Background
Previous Runtime Analyses of EDAs
Univariate Marginal Distribution Algorithm (UMDA)
Our Tool - Level-based Analysis
Non-elitist Processes
Level-based Theorem
Our Results
Warm up: LeadingOnes
Onemax and Feige’s Inequality
Conclusion
Runtime Analysis of EAs
Analysis of the time the EA requires to optimise a function f:
expected number of fitness evaluations
expressed asymptotically wrt instance size n
dependence on
characteristics of the problem
parameter settings of the EA
Previous Work
(1+1) EA cGA1
Onemax Θ(n log n) Θ(K
√
n) [Droste, 2006] EDA worse
Linear functions Θ(n log n) Ω(Kn) [Droste, 2006] EDA worse
(µ+1) EA cGA2
Onemax + N(0, σ2) superpoly(n) whp O(Kσ2√
n log Kn) [Friedrich et al., 2015] EDA better
(1+1) EA UMDA
LeadingOnes Θ(n2) O(λn), λ = ω(n2) [Chen et al., 2007]
BVLeadingOnes Θ(n2) ∞ w.o.p. [Chen et al., 2010] w/o margins
O(λn), λ = ω(n2) [Chen et al., 2010]
SubString 2Ω(n) w.o.p. O(λn), λ = ω(n2) [Chen et al., 2009] EDA better
1
K = n1/2+ε
2
K = ω(σ2√
n log n)
3
λ = Ω(log n)
Previous Work
(1+1) EA cGA1
Onemax Θ(n log n) Θ(K
√
n) [Droste, 2006] EDA worse
Linear functions Θ(n log n) Ω(Kn) [Droste, 2006] EDA worse
(µ+1) EA cGA2
Onemax + N(0, σ2) superpoly(n) whp O(Kσ2√
n log Kn) [Friedrich et al., 2015] EDA better
(1+1) EA UMDA
LeadingOnes Θ(n2) O(λn), λ = ω(n2) [Chen et al., 2007]
BVLeadingOnes Θ(n2) ∞ w.o.p. [Chen et al., 2010] w/o margins
O(λn), λ = ω(n2) [Chen et al., 2010]
SubString 2Ω(n) w.o.p. O(λn), λ = ω(n2) [Chen et al., 2009] EDA better
LeadingOnes Θ(n2) O(nλ log λ + n2) this paper3
Onemax Θ(n log n) O(nλ log λ) this paper
1
K = n1/2+ε
2
K = ω(σ2√
n log n)
3
λ = Ω(log n)
Univariate Marginal Distribution Algorithm
1: Initialise the vector p0 := (1/2, . . . , 1/2).
2: for t = 0, 1, 2, . . . do
3: Sample λ bitstrings y1, . . . , yλ according to the distribution
pt(x) =
n
i=1
pt(i)xi
(1 − pt(i))1−xi
4: Let y(1), . . . , y(λ) be the bitstrings sorted by fitness func. f
5: Compute the next vector pt+1 according to
pt+1(i) :=
Xi
µ
where Xi :=
µ
j=1
y
(j)
i
6: end for
Univariate Marginal Distribution Algorithm
1: Initialise the vector p0 := (1/2, . . . , 1/2).
2: for t = 0, 1, 2, . . . do
3: Sample λ bitstrings y1, . . . , yλ according to the distribution
pt(x) =
n
i=1
pt(i)xi
(1 − pt(i))1−xi
4: Let y(1), . . . , y(λ) be the bitstrings sorted by fitness func. f
5: Compute the next vector pt+1 according to
pt+1(i) :=



1
n if Xi = 0
Xi
µ if 1 ≤ Xi ≤ µ − 1
1 − 1
n if Xi = µ,
where Xi := µ
j=1 y
(j)
i .
6: end for
UMDA on Onemax (n = 5000)
0 10 20 30 40 50
0.00.20.40.60.81.0
iteration
Non-elitist populations
X
Pt+1 = (y1
, y2
, . . . , yλ
)
where yi
∼ D(Pt)
Non-elitist populations
X
Pt+1 = (y1
, y2
, . . . , yλ
)
where yi
∼ D(Pt)
Example (UMDA)
D(P)(x) :=
n
i=1
pxi
i (1 − pi)1−xi
Level-Based Theorem
D(Pt)
AmA1 Aj Aj+1 · · ·
Pt
γ0λ γλ
X = A1 ⊃ A2 ⊃ · · · ⊃ Am−1 ⊃ Am = A
Level-Based Theorem
≥ γ(1 + δ)
≥ zj
D(Pt)
A+
mA+
1
A+
j A+
j+1 · · ·
Pt
γ0λ γλ
Theorem (Corus, Dang, Ereemeev, Lehre (2014))
If for any level j < m and population P where
|P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ
an individual y ∼ D(P) is in Aj+1 with
Pr (y ∈ Aj+1) ≥
γ(1 + δ) if γ > 0
zj if γ = 0
and the population size λ is at least
λ = Ω ln(m/(δzj))/δ2
then level Am is reached in expected time
O

 1
δ5

m ln λ +
m
j=1
1
λzj



 .
LeadingOnes
LeadingOnes(x) :=
n
i=1
i
j=1
xi
LeadingOnes
LeadingOnes(x) :=
n
i=1
i
j=1
xi
Theorem
The expected optimisation time of UMDA with
λ ≥ b ln(n) for some constant b > 0,
λ > (1 + δ)eµ
on LeadingOnes is
O(nλ ln(λ) + n2
).
Proof idea
Level definition x ∈ Aj ⇐⇒ LeadingOnes(x) ≥ j
If |P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ > 0
then Pr(y ∈ Aj+1) ≥ γ(1+δ)
Proof idea
11111111111111111111********
11111111111111111111********
11111111111111111111********
11111111111111111110********
11111111111111111110********
11111111111111111110********
11111111111111111110********
****************************
****************************
****************************
Level definition x ∈ Aj ⇐⇒ LeadingOnes(x) ≥ j
If |P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ > 0
then Pr(y ∈ Aj+1) ≥ γ(1+δ)
Proof idea
11111111111111111111********
11111111111111111111********
11111111111111111111********
11111111111111111110********
11111111111111111110********
11111111111111111110********
11111111111111111110********
****************************
****************************
****************************
Level definition x ∈ Aj ⇐⇒ LeadingOnes(x) ≥ j
If |P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ > 0
then Pr(y ∈ Aj+1) = j+1
i=1 pi ≥ 1 − 1
n
j γλ
µ ≥ γλ
eµ ≥ γ(1+δ)
Onemax
Onemax(x) =
n
i=1
xi
Onemax
Onemax(x) =
n
i=1
xi
Theorem
The expected optimisation time of UMDA with
λ ≥ b ln(n) for some constant b > 0,
µ < min{λ/(13e), n}
on Onemax is
O(nλ ln λ).
Proof idea (ignoring margins)
Recall definition of UMDA
Probability for i-th position (assuming within margins)
pi :=
Xi
µ
where Xi :=
µ
j=1
y
(j)
i
Proof idea (ignoring margins)
Recall definition of UMDA
Probability for i-th position (assuming within margins)
pi :=
Xi
µ
where Xi :=
µ
j=1
y
(j)
i
Definition of levels and a first observation
Choosing levels x ∈ Aj ⇐⇒ Onemax(x) ≥ j, need to show
|P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ (1)
=⇒ Pr (Y ∈ Aj+1) ≥ γ(1 + δ) (2)
Note that assumption (1) with γ0 := µ/λ implies
n
i=1
Xi ≥ µj + γλ
Proof idea (taking into account margins)
Proof idea (taking into account margins)
Pr (Y ∈ Aj+1) ≥ Pr Y1,k >
γλ
µ
+ j − · Pr (Yk+1,k+ +1 = )
≥ Pr Y1,k > E [Y1,k] −
γλ
12µ
· 1 −
1
n
Feige’s Inequality
i E [Yi]
Theorem
Given n independent r.v. Y1, . . . , Yn ∈ [0, 1], then for all δ > 0
Pr
n
i=1
Yi >
n
i=1
E [Yi] − δ ≥ min
1
13
,
δ
1 + δ
Proof idea
Pr (Y ∈ Aj+1) ≥ Pr Y1,k >
γλ
µ
+ j − · Pr (Yk+1,k+ +1 = µ )
≥ Pr Y1,k > E [Y1,k] −
γλ
12µ
· 1 −
1
n
≥ min
1
13
,
γλ
12µ
γλ
12µ + 1
·
1
e
≥
γλ
13eµ
Proof idea
Pr (Y ∈ Aj+1) ≥ Pr Y1,k >
γλ
µ
+ j − · Pr (Yk+1,k+ +1 = µ )
≥ Pr Y1,k > E [Y1,k] −
γλ
12µ
· 1 −
1
n
≥ min
1
13
,
γλ
12µ
γλ
12µ + 1
·
1
e
≥
γλ
13eµ
≥ γ(1 + δ) if λ ≥ 13e(1 + δ)µ
Conclusion and Future Work
The recent level-based method seems well suited for EDAs
Straightforward runtime analysis of the UMDA
Trivial analysis of LeadingOnes,
smaller populations suffice, i.e., O(ln n) vs ω(n2
)
First upper bound on Onemax
How tight are the upper bounds?
o(n ln n) on Onemax?
Other problems and algorithms
linear functions
multi-variate EDAs
Thank you
The research leading to these results has received funding from the
European Union Seventh Framework Programme (FP7/2007-2013)
under grant agreement no. 618091 (SAGE).
References
Chen, T., Lehre, P. K., Tang, K., and Yao, X. (2009).
When is an estimation of distribution algorithm better than an evolutionary
algorithm?
In Proceedings of the 10th IEEE Congress on Evolutionary Computation
(CEC 2009), pages 1470–1477. IEEE.
Chen, T., Tang, K., Chen, G., and Yao, X. (2007).
On the analysis of average time complexity of estimation of distribution
algorithms.
In Proceedings of 2007 IEEE Congress on Evolutionary Computation (CEC’07),
pages 453–460.
Chen, T., Tang, K., Chen, G., and Yao, X. (2010).
Analysis of computational time of simple estimation of distribution algorithms.
IEEE Trans. Evolutionary Computation, 14(1):1–22.
Droste, S. (2006).
A rigorous analysis of the compact genetic algorithm for linear functions.
Natural Computing, 5(3):257–283.
Friedrich, T., K¨otzing, T., Krejca, M. S., and Sutton, A. M. (2015).
The benefit of sex in noisy evolutionary search.
CoRR, abs/1502.02793.

Weitere ähnliche Inhalte

Was ist angesagt?

GradStudentSeminarSept30
GradStudentSeminarSept30GradStudentSeminarSept30
GradStudentSeminarSept30
Ryan White
 

Was ist angesagt? (19)

A new Perron-Frobenius theorem for nonnegative tensors
A new Perron-Frobenius theorem for nonnegative tensorsA new Perron-Frobenius theorem for nonnegative tensors
A new Perron-Frobenius theorem for nonnegative tensors
 
Low Complexity Regularization of Inverse Problems - Course #3 Proximal Splitt...
Low Complexity Regularization of Inverse Problems - Course #3 Proximal Splitt...Low Complexity Regularization of Inverse Problems - Course #3 Proximal Splitt...
Low Complexity Regularization of Inverse Problems - Course #3 Proximal Splitt...
 
IVR - Chapter 1 - Introduction
IVR - Chapter 1 - IntroductionIVR - Chapter 1 - Introduction
IVR - Chapter 1 - Introduction
 
22 01 2014_03_23_31_eee_formula_sheet_final
22 01 2014_03_23_31_eee_formula_sheet_final22 01 2014_03_23_31_eee_formula_sheet_final
22 01 2014_03_23_31_eee_formula_sheet_final
 
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
Nodal Domain Theorem for the p-Laplacian on Graphs and the Related Multiway C...
 
Proximal Splitting and Optimal Transport
Proximal Splitting and Optimal TransportProximal Splitting and Optimal Transport
Proximal Splitting and Optimal Transport
 
Tensor train to solve stochastic PDEs
Tensor train to solve stochastic PDEsTensor train to solve stochastic PDEs
Tensor train to solve stochastic PDEs
 
Signal Processing Course : Convex Optimization
Signal Processing Course : Convex OptimizationSignal Processing Course : Convex Optimization
Signal Processing Course : Convex Optimization
 
Gibbs flow transport for Bayesian inference
Gibbs flow transport for Bayesian inferenceGibbs flow transport for Bayesian inference
Gibbs flow transport for Bayesian inference
 
Signal Processing Course : Inverse Problems Regularization
Signal Processing Course : Inverse Problems RegularizationSignal Processing Course : Inverse Problems Regularization
Signal Processing Course : Inverse Problems Regularization
 
sada_pres
sada_pressada_pres
sada_pres
 
An application of the hyperfunction theory to numerical integration
An application of the hyperfunction theory to numerical integrationAn application of the hyperfunction theory to numerical integration
An application of the hyperfunction theory to numerical integration
 
GradStudentSeminarSept30
GradStudentSeminarSept30GradStudentSeminarSept30
GradStudentSeminarSept30
 
2018 MUMS Fall Course - Bayesian inference for model calibration in UQ - Ralp...
2018 MUMS Fall Course - Bayesian inference for model calibration in UQ - Ralp...2018 MUMS Fall Course - Bayesian inference for model calibration in UQ - Ralp...
2018 MUMS Fall Course - Bayesian inference for model calibration in UQ - Ralp...
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 
Low Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
Low Complexity Regularization of Inverse Problems - Course #1 Inverse ProblemsLow Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
Low Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
 
Model Selection with Piecewise Regular Gauges
Model Selection with Piecewise Regular GaugesModel Selection with Piecewise Regular Gauges
Model Selection with Piecewise Regular Gauges
 
H2O World - Consensus Optimization and Machine Learning - Stephen Boyd
H2O World - Consensus Optimization and Machine Learning - Stephen BoydH2O World - Consensus Optimization and Machine Learning - Stephen Boyd
H2O World - Consensus Optimization and Machine Learning - Stephen Boyd
 
Learning Sparse Representation
Learning Sparse RepresentationLearning Sparse Representation
Learning Sparse Representation
 

Andere mochten auch

Young marketers 3 the final round - dinh thien phuoc
Young marketers 3   the final round - dinh thien phuocYoung marketers 3   the final round - dinh thien phuoc
Young marketers 3 the final round - dinh thien phuoc
Đinh Phước
 

Andere mochten auch (14)

Planetes sòlidis sistema solar
Planetes sòlidis sistema solarPlanetes sòlidis sistema solar
Planetes sòlidis sistema solar
 
Els planetes gasosos
Els planetes gasososEls planetes gasosos
Els planetes gasosos
 
Cometes i asteroides
Cometes i asteroidesCometes i asteroides
Cometes i asteroides
 
Yemek+
Yemek+Yemek+
Yemek+
 
HRSS and info:HR
HRSS and info:HRHRSS and info:HR
HRSS and info:HR
 
Les galàxies
Les galàxiesLes galàxies
Les galàxies
 
La lluna
La llunaLa lluna
La lluna
 
EduWave Introduction
EduWave IntroductionEduWave Introduction
EduWave Introduction
 
La terra
La terraLa terra
La terra
 
DTP Powerpoint Concept #1
DTP Powerpoint Concept #1DTP Powerpoint Concept #1
DTP Powerpoint Concept #1
 
Les estrelles
Les estrellesLes estrelles
Les estrelles
 
[YM3] crazy team
[YM3] crazy team[YM3] crazy team
[YM3] crazy team
 
Young marketers 3 the final round - dinh thien phuoc
Young marketers 3   the final round - dinh thien phuocYoung marketers 3   the final round - dinh thien phuoc
Young marketers 3 the final round - dinh thien phuoc
 
Young Marketers - [Crazy Team]
Young Marketers - [Crazy Team]Young Marketers - [Crazy Team]
Young Marketers - [Crazy Team]
 

Ähnlich wie Simplified Runtime Analysis of Estimation of Distribution Algorithms

Runtime Analysis of Population-based Evolutionary Algorithms
Runtime Analysis of Population-based Evolutionary AlgorithmsRuntime Analysis of Population-based Evolutionary Algorithms
Runtime Analysis of Population-based Evolutionary Algorithms
Per Kristian Lehre
 
Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...
Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...
Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...
Chiheb Ben Hammouda
 
2014 spring crunch seminar (SDE/levy/fractional/spectral method)
2014 spring crunch seminar (SDE/levy/fractional/spectral method)2014 spring crunch seminar (SDE/levy/fractional/spectral method)
2014 spring crunch seminar (SDE/levy/fractional/spectral method)
Zheng Mengdi
 
KAUST_talk_short.pdf
KAUST_talk_short.pdfKAUST_talk_short.pdf
KAUST_talk_short.pdf
Chiheb Ben Hammouda
 

Ähnlich wie Simplified Runtime Analysis of Estimation of Distribution Algorithms (20)

Runtime Analysis of Population-based Evolutionary Algorithms
Runtime Analysis of Population-based Evolutionary AlgorithmsRuntime Analysis of Population-based Evolutionary Algorithms
Runtime Analysis of Population-based Evolutionary Algorithms
 
Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...
Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...
Seminar Talk: Multilevel Hybrid Split Step Implicit Tau-Leap for Stochastic R...
 
A Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeA Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cube
 
Improving estimates for discrete polynomial averaging operators
Improving estimates for discrete polynomial averaging operatorsImproving estimates for discrete polynomial averaging operators
Improving estimates for discrete polynomial averaging operators
 
2014 spring crunch seminar (SDE/levy/fractional/spectral method)
2014 spring crunch seminar (SDE/levy/fractional/spectral method)2014 spring crunch seminar (SDE/levy/fractional/spectral method)
2014 spring crunch seminar (SDE/levy/fractional/spectral method)
 
QMC: Operator Splitting Workshop, Perturbed (accelerated) Proximal-Gradient A...
QMC: Operator Splitting Workshop, Perturbed (accelerated) Proximal-Gradient A...QMC: Operator Splitting Workshop, Perturbed (accelerated) Proximal-Gradient A...
QMC: Operator Splitting Workshop, Perturbed (accelerated) Proximal-Gradient A...
 
Low rank tensor approximation of probability density and characteristic funct...
Low rank tensor approximation of probability density and characteristic funct...Low rank tensor approximation of probability density and characteristic funct...
Low rank tensor approximation of probability density and characteristic funct...
 
Distributed solution of stochastic optimal control problem on GPUs
Distributed solution of stochastic optimal control problem on GPUsDistributed solution of stochastic optimal control problem on GPUs
Distributed solution of stochastic optimal control problem on GPUs
 
Optimal interval clustering: Application to Bregman clustering and statistica...
Optimal interval clustering: Application to Bregman clustering and statistica...Optimal interval clustering: Application to Bregman clustering and statistica...
Optimal interval clustering: Application to Bregman clustering and statistica...
 
Mcqmc talk
Mcqmc talkMcqmc talk
Mcqmc talk
 
Reading Seminar (140515) Spectral Learning of L-PCFGs
Reading Seminar (140515) Spectral Learning of L-PCFGsReading Seminar (140515) Spectral Learning of L-PCFGs
Reading Seminar (140515) Spectral Learning of L-PCFGs
 
MLP輪読スパース8章 トレースノルム正則化
MLP輪読スパース8章 トレースノルム正則化MLP輪読スパース8章 トレースノルム正則化
MLP輪読スパース8章 トレースノルム正則化
 
The Universal Bayesian Chow-Liu Algorithm
The Universal Bayesian Chow-Liu AlgorithmThe Universal Bayesian Chow-Liu Algorithm
The Universal Bayesian Chow-Liu Algorithm
 
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
Higher-order Factorization Machines(第5回ステアラボ人工知能セミナー)
 
stochastic processes assignment help
stochastic processes assignment helpstochastic processes assignment help
stochastic processes assignment help
 
KAUST_talk_short.pdf
KAUST_talk_short.pdfKAUST_talk_short.pdf
KAUST_talk_short.pdf
 
A Mathematically Derived Number of Resamplings for Noisy Optimization (GECCO2...
A Mathematically Derived Number of Resamplings for Noisy Optimization (GECCO2...A Mathematically Derived Number of Resamplings for Noisy Optimization (GECCO2...
A Mathematically Derived Number of Resamplings for Noisy Optimization (GECCO2...
 
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
QMC Program: Trends and Advances in Monte Carlo Sampling Algorithms Workshop,...
 
A Szemerédi-type theorem for subsets of the unit cube
A Szemerédi-type theorem for subsets of the unit cubeA Szemerédi-type theorem for subsets of the unit cube
A Szemerédi-type theorem for subsets of the unit cube
 
Murphy: Machine learning A probabilistic perspective: Ch.9
Murphy: Machine learning A probabilistic perspective: Ch.9Murphy: Machine learning A probabilistic perspective: Ch.9
Murphy: Machine learning A probabilistic perspective: Ch.9
 

Kürzlich hochgeladen

Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
Areesha Ahmad
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Sérgio Sacani
 
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
Lokesh Kothari
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
Areesha Ahmad
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Sérgio Sacani
 
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
ssuser79fe74
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Sérgio Sacani
 

Kürzlich hochgeladen (20)

Clean In Place(CIP).pptx .
Clean In Place(CIP).pptx                 .Clean In Place(CIP).pptx                 .
Clean In Place(CIP).pptx .
 
Conjugation, transduction and transformation
Conjugation, transduction and transformationConjugation, transduction and transformation
Conjugation, transduction and transformation
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICESAMASTIPUR CALL GIRL 7857803690  LOW PRICE  ESCORT SERVICE
SAMASTIPUR CALL GIRL 7857803690 LOW PRICE ESCORT SERVICE
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
 
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
GUIDELINES ON SIMILAR BIOLOGICS Regulatory Requirements for Marketing Authori...
 
Bacterial Identification and Classifications
Bacterial Identification and ClassificationsBacterial Identification and Classifications
Bacterial Identification and Classifications
 
Call Girls Alandi Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Alandi Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Alandi Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Alandi Call Me 7737669865 Budget Friendly No Advance Booking
 
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
High Class Escorts in Hyderabad ₹7.5k Pick Up & Drop With Cash Payment 969456...
 
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 bAsymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
Asymmetry in the atmosphere of the ultra-hot Jupiter WASP-76 b
 
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptxCOST ESTIMATION FOR A RESEARCH PROJECT.pptx
COST ESTIMATION FOR A RESEARCH PROJECT.pptx
 
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 60009654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
9654467111 Call Girls In Raj Nagar Delhi Short 1500 Night 6000
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
High Profile 🔝 8250077686 📞 Call Girls Service in GTB Nagar🍑
 
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verifiedConnaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
Connaught Place, Delhi Call girls :8448380779 Model Escorts | 100% verified
 
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
Chemical Tests; flame test, positive and negative ions test Edexcel Internati...
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Factory Acceptance Test( FAT).pptx .
Factory Acceptance Test( FAT).pptx       .Factory Acceptance Test( FAT).pptx       .
Factory Acceptance Test( FAT).pptx .
 

Simplified Runtime Analysis of Estimation of Distribution Algorithms

  • 1. Simplified Runtime Analysis of Estimation of Distribution Algorithms Duc-Cuong Dang Per Kristian Lehre University of Nottingham United Kingdom Madrid, Spain July, 11-15th 2015
  • 2. Outline Background Previous Runtime Analyses of EDAs Univariate Marginal Distribution Algorithm (UMDA) Our Tool - Level-based Analysis Non-elitist Processes Level-based Theorem Our Results Warm up: LeadingOnes Onemax and Feige’s Inequality Conclusion
  • 3. Runtime Analysis of EAs Analysis of the time the EA requires to optimise a function f: expected number of fitness evaluations expressed asymptotically wrt instance size n dependence on characteristics of the problem parameter settings of the EA
  • 4. Previous Work (1+1) EA cGA1 Onemax Θ(n log n) Θ(K √ n) [Droste, 2006] EDA worse Linear functions Θ(n log n) Ω(Kn) [Droste, 2006] EDA worse (µ+1) EA cGA2 Onemax + N(0, σ2) superpoly(n) whp O(Kσ2√ n log Kn) [Friedrich et al., 2015] EDA better (1+1) EA UMDA LeadingOnes Θ(n2) O(λn), λ = ω(n2) [Chen et al., 2007] BVLeadingOnes Θ(n2) ∞ w.o.p. [Chen et al., 2010] w/o margins O(λn), λ = ω(n2) [Chen et al., 2010] SubString 2Ω(n) w.o.p. O(λn), λ = ω(n2) [Chen et al., 2009] EDA better 1 K = n1/2+ε 2 K = ω(σ2√ n log n) 3 λ = Ω(log n)
  • 5. Previous Work (1+1) EA cGA1 Onemax Θ(n log n) Θ(K √ n) [Droste, 2006] EDA worse Linear functions Θ(n log n) Ω(Kn) [Droste, 2006] EDA worse (µ+1) EA cGA2 Onemax + N(0, σ2) superpoly(n) whp O(Kσ2√ n log Kn) [Friedrich et al., 2015] EDA better (1+1) EA UMDA LeadingOnes Θ(n2) O(λn), λ = ω(n2) [Chen et al., 2007] BVLeadingOnes Θ(n2) ∞ w.o.p. [Chen et al., 2010] w/o margins O(λn), λ = ω(n2) [Chen et al., 2010] SubString 2Ω(n) w.o.p. O(λn), λ = ω(n2) [Chen et al., 2009] EDA better LeadingOnes Θ(n2) O(nλ log λ + n2) this paper3 Onemax Θ(n log n) O(nλ log λ) this paper 1 K = n1/2+ε 2 K = ω(σ2√ n log n) 3 λ = Ω(log n)
  • 6. Univariate Marginal Distribution Algorithm 1: Initialise the vector p0 := (1/2, . . . , 1/2). 2: for t = 0, 1, 2, . . . do 3: Sample λ bitstrings y1, . . . , yλ according to the distribution pt(x) = n i=1 pt(i)xi (1 − pt(i))1−xi 4: Let y(1), . . . , y(λ) be the bitstrings sorted by fitness func. f 5: Compute the next vector pt+1 according to pt+1(i) := Xi µ where Xi := µ j=1 y (j) i 6: end for
  • 7. Univariate Marginal Distribution Algorithm 1: Initialise the vector p0 := (1/2, . . . , 1/2). 2: for t = 0, 1, 2, . . . do 3: Sample λ bitstrings y1, . . . , yλ according to the distribution pt(x) = n i=1 pt(i)xi (1 − pt(i))1−xi 4: Let y(1), . . . , y(λ) be the bitstrings sorted by fitness func. f 5: Compute the next vector pt+1 according to pt+1(i) :=    1 n if Xi = 0 Xi µ if 1 ≤ Xi ≤ µ − 1 1 − 1 n if Xi = µ, where Xi := µ j=1 y (j) i . 6: end for
  • 8. UMDA on Onemax (n = 5000) 0 10 20 30 40 50 0.00.20.40.60.81.0 iteration
  • 9. Non-elitist populations X Pt+1 = (y1 , y2 , . . . , yλ ) where yi ∼ D(Pt)
  • 10. Non-elitist populations X Pt+1 = (y1 , y2 , . . . , yλ ) where yi ∼ D(Pt) Example (UMDA) D(P)(x) := n i=1 pxi i (1 − pi)1−xi
  • 11. Level-Based Theorem D(Pt) AmA1 Aj Aj+1 · · · Pt γ0λ γλ X = A1 ⊃ A2 ⊃ · · · ⊃ Am−1 ⊃ Am = A
  • 12. Level-Based Theorem ≥ γ(1 + δ) ≥ zj D(Pt) A+ mA+ 1 A+ j A+ j+1 · · · Pt γ0λ γλ Theorem (Corus, Dang, Ereemeev, Lehre (2014)) If for any level j < m and population P where |P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ an individual y ∼ D(P) is in Aj+1 with Pr (y ∈ Aj+1) ≥ γ(1 + δ) if γ > 0 zj if γ = 0 and the population size λ is at least λ = Ω ln(m/(δzj))/δ2 then level Am is reached in expected time O   1 δ5  m ln λ + m j=1 1 λzj     .
  • 14. LeadingOnes LeadingOnes(x) := n i=1 i j=1 xi Theorem The expected optimisation time of UMDA with λ ≥ b ln(n) for some constant b > 0, λ > (1 + δ)eµ on LeadingOnes is O(nλ ln(λ) + n2 ).
  • 15. Proof idea Level definition x ∈ Aj ⇐⇒ LeadingOnes(x) ≥ j If |P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ > 0 then Pr(y ∈ Aj+1) ≥ γ(1+δ)
  • 19. Onemax Onemax(x) = n i=1 xi Theorem The expected optimisation time of UMDA with λ ≥ b ln(n) for some constant b > 0, µ < min{λ/(13e), n} on Onemax is O(nλ ln λ).
  • 20. Proof idea (ignoring margins) Recall definition of UMDA Probability for i-th position (assuming within margins) pi := Xi µ where Xi := µ j=1 y (j) i
  • 21. Proof idea (ignoring margins) Recall definition of UMDA Probability for i-th position (assuming within margins) pi := Xi µ where Xi := µ j=1 y (j) i Definition of levels and a first observation Choosing levels x ∈ Aj ⇐⇒ Onemax(x) ≥ j, need to show |P ∩ Aj| ≥ γ0λ > |P ∩ Aj+1| =: γλ (1) =⇒ Pr (Y ∈ Aj+1) ≥ γ(1 + δ) (2) Note that assumption (1) with γ0 := µ/λ implies n i=1 Xi ≥ µj + γλ
  • 22. Proof idea (taking into account margins)
  • 23. Proof idea (taking into account margins) Pr (Y ∈ Aj+1) ≥ Pr Y1,k > γλ µ + j − · Pr (Yk+1,k+ +1 = ) ≥ Pr Y1,k > E [Y1,k] − γλ 12µ · 1 − 1 n
  • 24. Feige’s Inequality i E [Yi] Theorem Given n independent r.v. Y1, . . . , Yn ∈ [0, 1], then for all δ > 0 Pr n i=1 Yi > n i=1 E [Yi] − δ ≥ min 1 13 , δ 1 + δ
  • 25. Proof idea Pr (Y ∈ Aj+1) ≥ Pr Y1,k > γλ µ + j − · Pr (Yk+1,k+ +1 = µ ) ≥ Pr Y1,k > E [Y1,k] − γλ 12µ · 1 − 1 n ≥ min 1 13 , γλ 12µ γλ 12µ + 1 · 1 e ≥ γλ 13eµ
  • 26. Proof idea Pr (Y ∈ Aj+1) ≥ Pr Y1,k > γλ µ + j − · Pr (Yk+1,k+ +1 = µ ) ≥ Pr Y1,k > E [Y1,k] − γλ 12µ · 1 − 1 n ≥ min 1 13 , γλ 12µ γλ 12µ + 1 · 1 e ≥ γλ 13eµ ≥ γ(1 + δ) if λ ≥ 13e(1 + δ)µ
  • 27. Conclusion and Future Work The recent level-based method seems well suited for EDAs Straightforward runtime analysis of the UMDA Trivial analysis of LeadingOnes, smaller populations suffice, i.e., O(ln n) vs ω(n2 ) First upper bound on Onemax How tight are the upper bounds? o(n ln n) on Onemax? Other problems and algorithms linear functions multi-variate EDAs
  • 28. Thank you The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 618091 (SAGE).
  • 29. References Chen, T., Lehre, P. K., Tang, K., and Yao, X. (2009). When is an estimation of distribution algorithm better than an evolutionary algorithm? In Proceedings of the 10th IEEE Congress on Evolutionary Computation (CEC 2009), pages 1470–1477. IEEE. Chen, T., Tang, K., Chen, G., and Yao, X. (2007). On the analysis of average time complexity of estimation of distribution algorithms. In Proceedings of 2007 IEEE Congress on Evolutionary Computation (CEC’07), pages 453–460. Chen, T., Tang, K., Chen, G., and Yao, X. (2010). Analysis of computational time of simple estimation of distribution algorithms. IEEE Trans. Evolutionary Computation, 14(1):1–22. Droste, S. (2006). A rigorous analysis of the compact genetic algorithm for linear functions. Natural Computing, 5(3):257–283. Friedrich, T., K¨otzing, T., Krejca, M. S., and Sutton, A. M. (2015). The benefit of sex in noisy evolutionary search. CoRR, abs/1502.02793.