SlideShare uma empresa Scribd logo
1 de 29
Baixar para ler offline
MarkovChainMonteCarlo
theory and worked examples




                             Dario Digiuni,
                             A.A. 2007/2008
Markov Chain Monte Carlo
• Class of sampling algorithms

• High sampling efficiency

• Sample from a distribution with unknown normalization constant

• Often the only way to solve problems in time polynomial in the
  number of dimensions
       e.g. evaluation of a convex body volume
MCMC: applications
   • Statistical Mechanics
     Metropolis-Hastings



   • Optimization
     ▫ Simulated annealing




   • Bayesian Inference
     ▫ Metropolis-Hastings
     ▫ Gibbs sampling
The Monte Carlo principle
• Sample a set of N independent and identically-distributed variables




• Approximation of the target p.d.f. with the empirical expression




       … then approximation of the integrals!
Rejection Sampling
  1. It needs finding M!
  2. Low acceptance rate
Idea
• I can use the previously sampled value to find the following one

• Exploration of the configuration space by means of Markov Chains:




       def .: Markov process




       def .: Markov chain
Invariant distribution
 • Stability conditions:

   1. Irreducibility= for every state there exists a finite probability to visit
      any other state
   2. Aperiodicity = there are no loops.

 • Sufficient condition
   1. Detailed balance principle




 MCMC algorithms are aperiodic, irreducible Markov chains having
  the target pdf as the invariant distribution
Example
• What is the probability to find the lift at the ground floor in a three
  floor building?

  ▫ 3 states Markov chain




  ▫ Lift= Random Walker

  ▫ Transition matrix




  ▫ Looking for the invariant distribution
      … burn-in …
Example - 2
• I can apply the matrix T on the right to any of the states, e.g.



                                                          homogeneous
                                                          Markov chain




                                               ~ 50% is the probability to find
• Google’s PageRank:                               the lift at the ground floor

  ▫ Websites are the states, T is defined by the number of hyperlinks among
    them and the user is the random walker:

      The webpages are displayed following the invariant distribution!
Metropolis-Hastings
• Given the target distribution
                                                          equivalent to T
  1.   Choose a value for

  2.   Sample from a proposal distribution

  3.   Accept the new value with probability




  4.   Return to 1
                  Ratio independent            Equal in Metropolis algorithm
                 of the normalization!
M.-H. – Pros and Cons
• Very general sampling method:

  ▫ I can sample from a unnormalized distribution

  ▫ It does not require to provide upper bound for the function



• Good working depends on the choice of the proposal distribution

  ▫ well-mixing condition
M.-H. - Example
• In Statistical Mechanics it is important to evalue the partition
  function,

  e.g. Ising model
                                                   Sum every possible spin state:
                                                     In a 10 x 10 x 10 spin cube,
                                                      I would have to sum over
 MCMC APPROACH:

 1. Evaluate the system’s energy                   Possible states = UNFEASIBLE

 2. Pick up a spin at random and flip it:

     1. If energy decreases, this is the new spin configuration

     2. If energy increases, this is the new spin configuration with
        probability
Simulated Annealing
• It allows one to find the global maximum of a generic pdf

  ▫ No comparison between the value of local minima required
  ▫ Application to the maximum-likelihood method

• It is a non-homogeneous Markov chain whose invariant distribution
  keeps changing as follows:
Simulated Annealing: example
  • Let us apply the algorithm to a simple, 1-dimensional case

  • The optimal cooling scheme is
Simulated Annealing: Pros and Cons
• The global maximum is univocally determined
  ▫ Even if walker starts next to a local (non global!) maximum, it converges to the
    true global maximum




• It requires a good tuning of the parameters
Gibbs Sampler
• Optimal method to marginalize multidimensional distributions

• Let us assume we have a n-dimensional vector and that we know all
  the conditional probability expression for the pdf




• We take the following proposal distribution:
Gibbs Sampler - 2
• Then:




                    very efficient
                      method!
Gibbs Sampler – practically
Gibbs Sampler – practically
1.       §Initialize              fix n-1 coordinates and sample
                                  from the resulting pdf

2.       for (i=0 ; i < N; i++)

     •     Sample

     •     Sample

     •     Sample




     •     Sample
Gibbs Sampler – example




• Let us pretend we cannot determine the normalization
  constant…




  … but we can make a comparison with the true marginalized
    pdf…
Gibbs Sampler – results
                • Comparison      between      Gibbs
                  Sampling and the true M.-H.
                  sampling from the marginalized pdf


                             • Good c2 agreement
A complex MCMC application
 A radioactive source decays with frequency l1 and a detector records
   only every k1 –th event, then at the moment tc the decay rate
 changes to l2 and only one event out ofk2 is recorded.



 Apparently l1 , k1 , tc , l2 and k2 are undetermined.


         We wish to find them.
Preparation
• The waiting time for the k-th event in a Poissonian process with
  frequency l is distributed according to:




• I can sample a big amount of events from this pdf, changing the
  parameters l1 e k1 to l2 e k2 at time tc

• I evaluate the likelihood:
Idea
• I assume log-likelihood to be the invariant distribution!
  ▫ which are the Markov chain states?

        struct State {
                                                 Parameter
            double lambda1, lambda2;
                                                 space
            double tc;
            int k1, k2;                          Corresponding log-
            double plog;                         likelihood value

           State(double la1, double la2, double t, int kk1, int kk2) :

                       lambda1(la1), lambda2(la2), tc(t), k1(kk1), k2(kk2) {}

         State() {};
        };
Practically
• I have to find an appropriate proposal distribution to move among
  the states
  ▫ Attention: varying li and ki I have toi prevent the acceptance rate to be
    too low… but also too high!

• The a ratio is evaluated as the ratio between the final-state and
  initial-state likelihood values.

• Try to guess the values for li , ki and tc

• Let the chain evolve for a burn-in time and then record the results.
Results   • Even if the inital guess is quite far from the real
            value, the random walker converges.
            guess:          l1=5      l2 = 5   k1 = 3    k2 = 2


            real:           l1=1      l2 = 2   k1 = 1,   k2 = 1
Results- 2
  • Estimate of the uncertainty




                                  l2

                       l1
Results- 3
    • All the parameters can be detemined quickly
      guess:        tc=150           real:    tc=300
References
• C. Andrieu, N. De Freitas, A. Doucet e M.I. Jordan, Machine Learning 50
  (2003), 5-43.

• G. Casella e E.I. George, The American Statistician 46, 3 (1992), 167-174.

• W.H. Press, S. A. Teukolsky, W.T. Vetterling e B.P. Flannery, Numerical
  Recipes , Third Edition, Cambridge University Press, 2007.

• M. Loreti, Teoria degli errori e fondamenti di statistica, Decibel, Zanichelli
  (1998).

• B. Walsh, Markov Chain Monte Carlo and Gibbs Sampling, Lecture Notes
  for EEB 581

Mais conteúdo relacionado

Mais procurados

Mais procurados (20)

Lecture: Monte Carlo Methods
Lecture: Monte Carlo MethodsLecture: Monte Carlo Methods
Lecture: Monte Carlo Methods
 
07 Analysis of Algorithms: Order Statistics
07 Analysis of Algorithms: Order Statistics07 Analysis of Algorithms: Order Statistics
07 Analysis of Algorithms: Order Statistics
 
Pseudo Random Number Generators
Pseudo Random Number GeneratorsPseudo Random Number Generators
Pseudo Random Number Generators
 
Hidden Markov Model
Hidden Markov Model Hidden Markov Model
Hidden Markov Model
 
A short history of MCMC
A short history of MCMCA short history of MCMC
A short history of MCMC
 
Markov Chains
Markov ChainsMarkov Chains
Markov Chains
 
Moment generating function
Moment generating functionMoment generating function
Moment generating function
 
Hidden Markov Model - The Most Probable Path
Hidden Markov Model - The Most Probable PathHidden Markov Model - The Most Probable Path
Hidden Markov Model - The Most Probable Path
 
GMM
GMMGMM
GMM
 
Hidden Markov Model paper presentation
Hidden Markov Model paper presentationHidden Markov Model paper presentation
Hidden Markov Model paper presentation
 
An introduction to Bayesian Statistics using Python
An introduction to Bayesian Statistics using PythonAn introduction to Bayesian Statistics using Python
An introduction to Bayesian Statistics using Python
 
Ch11 hmm
Ch11 hmmCh11 hmm
Ch11 hmm
 
Stat 2153 Stochastic Process and Markov chain
Stat 2153 Stochastic Process and Markov chainStat 2153 Stochastic Process and Markov chain
Stat 2153 Stochastic Process and Markov chain
 
Markov Random Field (MRF)
Markov Random Field (MRF)Markov Random Field (MRF)
Markov Random Field (MRF)
 
Hidden markov model ppt
Hidden markov model pptHidden markov model ppt
Hidden markov model ppt
 
Monte carlo simulation
Monte carlo simulationMonte carlo simulation
Monte carlo simulation
 
Kernel Method
Kernel MethodKernel Method
Kernel Method
 
Optimization/Gradient Descent
Optimization/Gradient DescentOptimization/Gradient Descent
Optimization/Gradient Descent
 
ML - Multiple Linear Regression
ML - Multiple Linear RegressionML - Multiple Linear Regression
ML - Multiple Linear Regression
 
Moving Average
Moving AverageMoving Average
Moving Average
 

Semelhante a Markov Chain Monte Carlo explained

Change Point Analysis
Change Point AnalysisChange Point Analysis
Change Point AnalysisMark Conway
 
머피의 머신러닝: 17장 Markov Chain and HMM
머피의 머신러닝: 17장  Markov Chain and HMM머피의 머신러닝: 17장  Markov Chain and HMM
머피의 머신러닝: 17장 Markov Chain and HMMJungkyu Lee
 
Graph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear AlgebraGraph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear AlgebraJason Riedy
 
Financial Networks III. Centrality and Systemic Importance
Financial Networks III. Centrality and Systemic ImportanceFinancial Networks III. Centrality and Systemic Importance
Financial Networks III. Centrality and Systemic ImportanceKimmo Soramaki
 
NMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINAL
NMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINALNMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINAL
NMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINALNadav Kravitz
 
Selection K in K-means Clustering
Selection K in K-means ClusteringSelection K in K-means Clustering
Selection K in K-means ClusteringJunghoon Kim
 
How to analyse bulk transcriptomic data using Deseq2
How to analyse bulk transcriptomic data using Deseq2How to analyse bulk transcriptomic data using Deseq2
How to analyse bulk transcriptomic data using Deseq2AdamCribbs1
 
Firefly exact MCMC for Big Data
Firefly exact MCMC for Big DataFirefly exact MCMC for Big Data
Firefly exact MCMC for Big DataGianvito Siciliano
 
A small debate of power of randomness
A small debate of power of randomnessA small debate of power of randomness
A small debate of power of randomnessAbner Chih Yi Huang
 
Sampling and Markov Chain Monte Carlo Techniques
Sampling and Markov Chain Monte Carlo TechniquesSampling and Markov Chain Monte Carlo Techniques
Sampling and Markov Chain Monte Carlo TechniquesTomasz Kusmierczyk
 
Quantum computing
Quantum computingQuantum computing
Quantum computingGAUTHAMG5
 
Flexible Memory Allocation in Kinetic Monte Carlo Simulations
Flexible Memory Allocation in Kinetic Monte Carlo SimulationsFlexible Memory Allocation in Kinetic Monte Carlo Simulations
Flexible Memory Allocation in Kinetic Monte Carlo SimulationsAaron Craig
 

Semelhante a Markov Chain Monte Carlo explained (20)

Change Point Analysis
Change Point AnalysisChange Point Analysis
Change Point Analysis
 
머피의 머신러닝: 17장 Markov Chain and HMM
머피의 머신러닝: 17장  Markov Chain and HMM머피의 머신러닝: 17장  Markov Chain and HMM
머피의 머신러닝: 17장 Markov Chain and HMM
 
sbs.pdf
sbs.pdfsbs.pdf
sbs.pdf
 
Graph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear AlgebraGraph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear Algebra
 
Financial Networks III. Centrality and Systemic Importance
Financial Networks III. Centrality and Systemic ImportanceFinancial Networks III. Centrality and Systemic Importance
Financial Networks III. Centrality and Systemic Importance
 
NMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINAL
NMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINALNMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINAL
NMK Developing and Evaluating Algorithms for Gaussian State Reconstruction FINAL
 
Fa18_P1.pptx
Fa18_P1.pptxFa18_P1.pptx
Fa18_P1.pptx
 
Presentation1
Presentation1Presentation1
Presentation1
 
Selection K in K-means Clustering
Selection K in K-means ClusteringSelection K in K-means Clustering
Selection K in K-means Clustering
 
How to analyse bulk transcriptomic data using Deseq2
How to analyse bulk transcriptomic data using Deseq2How to analyse bulk transcriptomic data using Deseq2
How to analyse bulk transcriptomic data using Deseq2
 
Firefly exact MCMC for Big Data
Firefly exact MCMC for Big DataFirefly exact MCMC for Big Data
Firefly exact MCMC for Big Data
 
A small debate of power of randomness
A small debate of power of randomnessA small debate of power of randomness
A small debate of power of randomness
 
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...
 
Sampling and Markov Chain Monte Carlo Techniques
Sampling and Markov Chain Monte Carlo TechniquesSampling and Markov Chain Monte Carlo Techniques
Sampling and Markov Chain Monte Carlo Techniques
 
Quantum computing
Quantum computingQuantum computing
Quantum computing
 
Advanced Machine Learning
Advanced Machine LearningAdvanced Machine Learning
Advanced Machine Learning
 
rnn BASICS
rnn BASICSrnn BASICS
rnn BASICS
 
Lec10new
Lec10newLec10new
Lec10new
 
lec10new.ppt
lec10new.pptlec10new.ppt
lec10new.ppt
 
Flexible Memory Allocation in Kinetic Monte Carlo Simulations
Flexible Memory Allocation in Kinetic Monte Carlo SimulationsFlexible Memory Allocation in Kinetic Monte Carlo Simulations
Flexible Memory Allocation in Kinetic Monte Carlo Simulations
 

Último

Entrepreneurship lessons in Philippines
Entrepreneurship lessons in  PhilippinesEntrepreneurship lessons in  Philippines
Entrepreneurship lessons in PhilippinesDavidSamuel525586
 
MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?Olivia Kresic
 
International Business Environments and Operations 16th Global Edition test b...
International Business Environments and Operations 16th Global Edition test b...International Business Environments and Operations 16th Global Edition test b...
International Business Environments and Operations 16th Global Edition test b...ssuserf63bd7
 
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCRashishs7044
 
Cyber Security Training in Office Environment
Cyber Security Training in Office EnvironmentCyber Security Training in Office Environment
Cyber Security Training in Office Environmentelijahj01012
 
Appkodes Tinder Clone Script with Customisable Solutions.pptx
Appkodes Tinder Clone Script with Customisable Solutions.pptxAppkodes Tinder Clone Script with Customisable Solutions.pptx
Appkodes Tinder Clone Script with Customisable Solutions.pptxappkodes
 
Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!
Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!
Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!Doge Mining Website
 
Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.Anamaria Contreras
 
APRIL2024_UKRAINE_xml_0000000000000 .pdf
APRIL2024_UKRAINE_xml_0000000000000 .pdfAPRIL2024_UKRAINE_xml_0000000000000 .pdf
APRIL2024_UKRAINE_xml_0000000000000 .pdfRbc Rbcua
 
Organizational Structure Running A Successful Business
Organizational Structure Running A Successful BusinessOrganizational Structure Running A Successful Business
Organizational Structure Running A Successful BusinessSeta Wicaksana
 
8447779800, Low rate Call girls in Dwarka mor Delhi NCR
8447779800, Low rate Call girls in Dwarka mor Delhi NCR8447779800, Low rate Call girls in Dwarka mor Delhi NCR
8447779800, Low rate Call girls in Dwarka mor Delhi NCRashishs7044
 
Darshan Hiranandani [News About Next CEO].pdf
Darshan Hiranandani [News About Next CEO].pdfDarshan Hiranandani [News About Next CEO].pdf
Darshan Hiranandani [News About Next CEO].pdfShashank Mehta
 
Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737Riya Pathan
 
Memorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQMMemorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQMVoces Mineras
 
TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024Adnet Communications
 
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdfNewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdfKhaled Al Awadi
 
Buy gmail accounts.pdf Buy Old Gmail Accounts
Buy gmail accounts.pdf Buy Old Gmail AccountsBuy gmail accounts.pdf Buy Old Gmail Accounts
Buy gmail accounts.pdf Buy Old Gmail AccountsBuy Verified Accounts
 
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCREnjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCRalexsharmaa01
 

Último (20)

No-1 Call Girls In Goa 93193 VIP 73153 Escort service In North Goa Panaji, Ca...
No-1 Call Girls In Goa 93193 VIP 73153 Escort service In North Goa Panaji, Ca...No-1 Call Girls In Goa 93193 VIP 73153 Escort service In North Goa Panaji, Ca...
No-1 Call Girls In Goa 93193 VIP 73153 Escort service In North Goa Panaji, Ca...
 
Entrepreneurship lessons in Philippines
Entrepreneurship lessons in  PhilippinesEntrepreneurship lessons in  Philippines
Entrepreneurship lessons in Philippines
 
MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?MAHA Global and IPR: Do Actions Speak Louder Than Words?
MAHA Global and IPR: Do Actions Speak Louder Than Words?
 
International Business Environments and Operations 16th Global Edition test b...
International Business Environments and Operations 16th Global Edition test b...International Business Environments and Operations 16th Global Edition test b...
International Business Environments and Operations 16th Global Edition test b...
 
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
8447779800, Low rate Call girls in New Ashok Nagar Delhi NCR
 
Cyber Security Training in Office Environment
Cyber Security Training in Office EnvironmentCyber Security Training in Office Environment
Cyber Security Training in Office Environment
 
Appkodes Tinder Clone Script with Customisable Solutions.pptx
Appkodes Tinder Clone Script with Customisable Solutions.pptxAppkodes Tinder Clone Script with Customisable Solutions.pptx
Appkodes Tinder Clone Script with Customisable Solutions.pptx
 
Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!
Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!
Unlocking the Future: Explore Web 3.0 Workshop to Start Earning Today!
 
Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.Traction part 2 - EOS Model JAX Bridges.
Traction part 2 - EOS Model JAX Bridges.
 
Corporate Profile 47Billion Information Technology
Corporate Profile 47Billion Information TechnologyCorporate Profile 47Billion Information Technology
Corporate Profile 47Billion Information Technology
 
APRIL2024_UKRAINE_xml_0000000000000 .pdf
APRIL2024_UKRAINE_xml_0000000000000 .pdfAPRIL2024_UKRAINE_xml_0000000000000 .pdf
APRIL2024_UKRAINE_xml_0000000000000 .pdf
 
Organizational Structure Running A Successful Business
Organizational Structure Running A Successful BusinessOrganizational Structure Running A Successful Business
Organizational Structure Running A Successful Business
 
8447779800, Low rate Call girls in Dwarka mor Delhi NCR
8447779800, Low rate Call girls in Dwarka mor Delhi NCR8447779800, Low rate Call girls in Dwarka mor Delhi NCR
8447779800, Low rate Call girls in Dwarka mor Delhi NCR
 
Darshan Hiranandani [News About Next CEO].pdf
Darshan Hiranandani [News About Next CEO].pdfDarshan Hiranandani [News About Next CEO].pdf
Darshan Hiranandani [News About Next CEO].pdf
 
Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737Independent Call Girls Andheri Nightlaila 9967584737
Independent Call Girls Andheri Nightlaila 9967584737
 
Memorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQMMemorándum de Entendimiento (MoU) entre Codelco y SQM
Memorándum de Entendimiento (MoU) entre Codelco y SQM
 
TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024TriStar Gold Corporate Presentation - April 2024
TriStar Gold Corporate Presentation - April 2024
 
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdfNewBase  19 April  2024  Energy News issue - 1717 by Khaled Al Awadi.pdf
NewBase 19 April 2024 Energy News issue - 1717 by Khaled Al Awadi.pdf
 
Buy gmail accounts.pdf Buy Old Gmail Accounts
Buy gmail accounts.pdf Buy Old Gmail AccountsBuy gmail accounts.pdf Buy Old Gmail Accounts
Buy gmail accounts.pdf Buy Old Gmail Accounts
 
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCREnjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
Enjoy ➥8448380779▻ Call Girls In Sector 18 Noida Escorts Delhi NCR
 

Markov Chain Monte Carlo explained

  • 1. MarkovChainMonteCarlo theory and worked examples Dario Digiuni, A.A. 2007/2008
  • 2. Markov Chain Monte Carlo • Class of sampling algorithms • High sampling efficiency • Sample from a distribution with unknown normalization constant • Often the only way to solve problems in time polynomial in the number of dimensions e.g. evaluation of a convex body volume
  • 3. MCMC: applications • Statistical Mechanics Metropolis-Hastings • Optimization ▫ Simulated annealing • Bayesian Inference ▫ Metropolis-Hastings ▫ Gibbs sampling
  • 4. The Monte Carlo principle • Sample a set of N independent and identically-distributed variables • Approximation of the target p.d.f. with the empirical expression … then approximation of the integrals!
  • 5. Rejection Sampling 1. It needs finding M! 2. Low acceptance rate
  • 6. Idea • I can use the previously sampled value to find the following one • Exploration of the configuration space by means of Markov Chains: def .: Markov process def .: Markov chain
  • 7. Invariant distribution • Stability conditions: 1. Irreducibility= for every state there exists a finite probability to visit any other state 2. Aperiodicity = there are no loops. • Sufficient condition 1. Detailed balance principle MCMC algorithms are aperiodic, irreducible Markov chains having the target pdf as the invariant distribution
  • 8. Example • What is the probability to find the lift at the ground floor in a three floor building? ▫ 3 states Markov chain ▫ Lift= Random Walker ▫ Transition matrix ▫ Looking for the invariant distribution … burn-in …
  • 9. Example - 2 • I can apply the matrix T on the right to any of the states, e.g. homogeneous Markov chain ~ 50% is the probability to find • Google’s PageRank: the lift at the ground floor ▫ Websites are the states, T is defined by the number of hyperlinks among them and the user is the random walker:  The webpages are displayed following the invariant distribution!
  • 10. Metropolis-Hastings • Given the target distribution equivalent to T 1. Choose a value for 2. Sample from a proposal distribution 3. Accept the new value with probability 4. Return to 1 Ratio independent Equal in Metropolis algorithm of the normalization!
  • 11. M.-H. – Pros and Cons • Very general sampling method: ▫ I can sample from a unnormalized distribution ▫ It does not require to provide upper bound for the function • Good working depends on the choice of the proposal distribution ▫ well-mixing condition
  • 12. M.-H. - Example • In Statistical Mechanics it is important to evalue the partition function, e.g. Ising model Sum every possible spin state: In a 10 x 10 x 10 spin cube, I would have to sum over MCMC APPROACH: 1. Evaluate the system’s energy Possible states = UNFEASIBLE 2. Pick up a spin at random and flip it: 1. If energy decreases, this is the new spin configuration 2. If energy increases, this is the new spin configuration with probability
  • 13. Simulated Annealing • It allows one to find the global maximum of a generic pdf ▫ No comparison between the value of local minima required ▫ Application to the maximum-likelihood method • It is a non-homogeneous Markov chain whose invariant distribution keeps changing as follows:
  • 14. Simulated Annealing: example • Let us apply the algorithm to a simple, 1-dimensional case • The optimal cooling scheme is
  • 15. Simulated Annealing: Pros and Cons • The global maximum is univocally determined ▫ Even if walker starts next to a local (non global!) maximum, it converges to the true global maximum • It requires a good tuning of the parameters
  • 16. Gibbs Sampler • Optimal method to marginalize multidimensional distributions • Let us assume we have a n-dimensional vector and that we know all the conditional probability expression for the pdf • We take the following proposal distribution:
  • 17. Gibbs Sampler - 2 • Then: very efficient method!
  • 18. Gibbs Sampler – practically
  • 19. Gibbs Sampler – practically 1. §Initialize fix n-1 coordinates and sample from the resulting pdf 2. for (i=0 ; i < N; i++) • Sample • Sample • Sample • Sample
  • 20. Gibbs Sampler – example • Let us pretend we cannot determine the normalization constant… … but we can make a comparison with the true marginalized pdf…
  • 21. Gibbs Sampler – results • Comparison between Gibbs Sampling and the true M.-H. sampling from the marginalized pdf • Good c2 agreement
  • 22. A complex MCMC application A radioactive source decays with frequency l1 and a detector records only every k1 –th event, then at the moment tc the decay rate changes to l2 and only one event out ofk2 is recorded. Apparently l1 , k1 , tc , l2 and k2 are undetermined. We wish to find them.
  • 23. Preparation • The waiting time for the k-th event in a Poissonian process with frequency l is distributed according to: • I can sample a big amount of events from this pdf, changing the parameters l1 e k1 to l2 e k2 at time tc • I evaluate the likelihood:
  • 24. Idea • I assume log-likelihood to be the invariant distribution! ▫ which are the Markov chain states? struct State { Parameter double lambda1, lambda2; space double tc; int k1, k2; Corresponding log- double plog; likelihood value State(double la1, double la2, double t, int kk1, int kk2) : lambda1(la1), lambda2(la2), tc(t), k1(kk1), k2(kk2) {} State() {}; };
  • 25. Practically • I have to find an appropriate proposal distribution to move among the states ▫ Attention: varying li and ki I have toi prevent the acceptance rate to be too low… but also too high! • The a ratio is evaluated as the ratio between the final-state and initial-state likelihood values. • Try to guess the values for li , ki and tc • Let the chain evolve for a burn-in time and then record the results.
  • 26. Results • Even if the inital guess is quite far from the real value, the random walker converges. guess: l1=5 l2 = 5 k1 = 3 k2 = 2 real: l1=1 l2 = 2 k1 = 1, k2 = 1
  • 27. Results- 2 • Estimate of the uncertainty l2 l1
  • 28. Results- 3 • All the parameters can be detemined quickly guess: tc=150 real: tc=300
  • 29. References • C. Andrieu, N. De Freitas, A. Doucet e M.I. Jordan, Machine Learning 50 (2003), 5-43. • G. Casella e E.I. George, The American Statistician 46, 3 (1992), 167-174. • W.H. Press, S. A. Teukolsky, W.T. Vetterling e B.P. Flannery, Numerical Recipes , Third Edition, Cambridge University Press, 2007. • M. Loreti, Teoria degli errori e fondamenti di statistica, Decibel, Zanichelli (1998). • B. Walsh, Markov Chain Monte Carlo and Gibbs Sampling, Lecture Notes for EEB 581