0 Up votes0 Down votes

1 views2 pagesMay 08, 2014

© © All Rights Reserved

PDF, TXT or read online from Scribd

© All Rights Reserved

1 views

© All Rights Reserved

- Bright 1995
- UVa Problem List [Catagorized Algorithmic Problem]
- Triangular Sum Labeling NEW
- HTK
- Physica A. Szilard
- 440 Fall 2012 Final Solutions
- Exam Problems
- Casarotto
- Analytic Expressions for the Bit Error Probabilities of Rate 1-2 Memory 2 Convolutional Encoders
- DAA NOTES
- Geometric Mean Labeling
- Cp7201 Tfoc Model Qp 2 Theoretical Foundations of Computer Science
- Alrefrei_andradottir
- PQT PREVIOUS QUESTIONS @ DCE
- Magistarski 4599 Reliability
- Ban Dung Ryan 3
- Topic Detection and Tracking Using Hidden Markov Models
- DAA_Questions with answer.docx
- Multi-Agent Systems for the Simulation of Land-Use_GIS
- Recognition of Handwritten Names.pdf

You are on page 1of 2

5. Two faces of Markov processesinference and dynamics

Assigned Reading: Sections 4.9 and 4.10, Chapter 5, and Chapter 6 through section 8.

Problems to be handed in:

1 Estimation of the parameter of an exponential in additive exponential noise Suppose

an observation Y has the form Y = Z +N, where Z and N are independent, Z has the exponential

distribution with parameter , N has the exponential distribution with parameter one, and > 0

is an unknown parameter. We consider two approaches to nding

ML

(y).

(a) Show that f

cd

(y, z|) =

e

y+(1)z

0 z y

0 else

(b) Find f(y|). The direct approach to nding

ML

(y) is to maximize f(y|) (or its log) with

respect to . You neednt attempt the maximization.

(c) Derive the EM algorithm for nding

ML

(y). You may express your answer in terms of the

function dened by:

(y, ) = E[Z|y, ] =

1

1

y

exp((1)y)1

= 1

y

2

= 1

You neednt implement the algorithm.

2 Maximum likelihood estimation for HMMs Consider an HMM with unobserved data

Z = (Z

1

, . . . , Z

T

), observed data Y = (Y

1

, . . . , Y

T

), and parameter vector = (, A, B). Explain

how the forward-backward algorithm or the Viterbi algorithm can be used or modied to compute

the following:

(a) The ML estimator,

Z

ML

, of Z based on Y, assuming any initial state and any transitions i j

are possible for Z. (Hint: Your answer should not depend on or A.)

(b) The ML estimator,

Z

ML

, of Z based on Y, subject to the constraints that

Z

ML

takes values in

the set {z : P{Z = z} > 0}. (Hint: Your answer should depend on and A only through which

coordinates of and A are nonzero.)

(c) The ML estimator,

Z

1,ML

, of Z

1

based on Y.

(d) The ML estimator,

Z

to,ML

, of Z

to

based on Y, for some xed t

o

with 1 t

o

T.

3 Estimation of a critical transition time of hidden state in HMM Consider an HMM

with unobserved data Z = (Z

1

, . . . , Z

T

), observed data Y = (Y

1

, . . . , Y

T

), and parameter vector

= (, A, B). Let F {1, . . . , N

s

} and let

F

be the rst time t such that Z

t

F with the

convention that

F

= T + 1 if (Z

t

F for 1 t T).

(a) Describe how to nd the conditional distribution of

F

given Y, under the added assumption

that (a

i,j

= 0 for all (i, j) such that i F and j F), i.e. under the assumption that F is an

absorbing set for Z.

(b) Describe how to nd the conditional distribution of

F

given Y, without the added assumption

made in part (a).

1

4 On distributions of three discrete-time Markov processes For each of the Markov pro-

cesses with indicated one-step transition probability diagrams, determine the set of equilibrium

distributions and whether lim

t

n

(t) exists for all choices of the initial distribution, (0), and

all states n.

(c)

1 1

1

0.5

0.5

0 1 2 3

(a)

. . .

0 1

2

3

(b)

1/2

2/3

1/3 1

1/2 3/4

1/4

. . .

0 1

2

3

3/4

1/4

2/3

1/3

1/2

1/2

5 On distributions of three continuous-time Markov processes For each of the Markov

processes with indicated one-step transition probability diagrams, determine the set of equilibrium

distributions and whether lim

t

n

(t) exists for all choices of the initial distribution, (0), and

all states n. (The answer for (c) may depend on the value of c; assume c 0.)

2

(a)

1

2 3

4

2

3

9

5

0 1

2

3 . . .

(c)

1 1 1 1

1+c 1+c/2 1+c/3 1+c/4

0 1

2

3

(b)

. . .

1 1 1 1

2 2 2

6 Generating a random spanning tree Let G = (V, E) be an undirected, connected graph

with n vertices and m edges (so |V | = n and |E| = m). Suppose that m n, so the graph has at

least one cycle. A spanning tree of G is a subset T of E with cardinality n 1 and no cycles. Let

S denote the set of all spanning trees of G. We shall consider a Markov process with state space S;

the one-step transition probabilities are described as follows. Given a state T, an edge e is selected

at random from among the mn+1 edges in E T, with all such edges having equal probability.

The set T {e} then has a single cycle. One of the edges in the cycle (possibly edge e) is selected

at random, with all edges in the cycle having equal probability of being selected, and is removed

from T {e} to produce the next state, T

.

(a) Is the Markov process irreducible (for any choice of G satisfying the conditions given)? Justify

your answer.

(b) Is the Markov process aperiodic (for any graph G satisfying the conditions given)?

(c) Show that the one-step transition probability matrix P = (p

T,T

: T, T

S) is symmetric.

(d) Show that the equilibrium distribution assigns equal probability to all states in S. Hence, a

method for generating an approximately uniformly distributed spanning tree is to run the Markov

process a long time and occasionally sample it.

2

- Bright 1995Uploaded byDaniel Bogiatzis Gibbons
- UVa Problem List [Catagorized Algorithmic Problem]Uploaded bymr1r
- Triangular Sum Labeling NEWUploaded byMurugananthamParamasivam
- HTKUploaded byAshutosh Verma
- Physica A. SzilardUploaded byIon Nicu
- 440 Fall 2012 Final SolutionsUploaded byEd Z
- Exam ProblemsUploaded byVan Dungct
- CasarottoUploaded byEpic Win
- Analytic Expressions for the Bit Error Probabilities of Rate 1-2 Memory 2 Convolutional EncodersUploaded byvmaiz
- DAA NOTESUploaded byPraveen Kumar
- Geometric Mean LabelingUploaded byJoel Carredo
- Cp7201 Tfoc Model Qp 2 Theoretical Foundations of Computer ScienceUploaded byappasami
- Alrefrei_andradottirUploaded byalexandru_bratu_6
- PQT PREVIOUS QUESTIONS @ DCEUploaded byDhilip Prabakaran
- Magistarski 4599 ReliabilityUploaded byIrfan Ashraf
- Ban Dung Ryan 3Uploaded byRAJAT SHARMA
- Topic Detection and Tracking Using Hidden Markov ModelsUploaded byjavaria asif
- DAA_Questions with answer.docxUploaded byprianka rr
- Multi-Agent Systems for the Simulation of Land-Use_GISUploaded byguyndjeng
- Recognition of Handwritten Names.pdfUploaded bySaidZamora
- WomackUploaded byAnsari Rehan
- A Study on Minimum Cost Spanning TreeUploaded byJasmine Priskilla
- HTK Basic TutorialUploaded bylucianolnl
- 2. IJAMSS - Ores Theorem Labelled Graphs Face BookUploaded byiaset123
- assign5.psUploaded byvenugopal
- Non Parametric Estimation for Financial Investment Under Log-utilityUploaded byTraderCat Solaris
- Discrete hmmUploaded byEric Brugel
- Graph theoryUploaded byPralay Das
- IEEE Std 61 03 -1 989Uploaded byM B
- iedatamining-ijcaiws03Uploaded byNgô Hiền

- sol7Uploaded byThinh
- sol6Uploaded byThinh
- sol5Uploaded byThinh
- sol4Uploaded byThinh
- sol3Uploaded byThinh
- sol2Uploaded byThinh
- sol1Uploaded byThinh
- Quiz SolUploaded byThinh
- FinalUploaded byThinh
- exam2solUploaded byThinh
- QuizUploaded byThinh
- ps7Uploaded byThinh
- ps6Uploaded byThinh
- ps4Uploaded byThinh
- ps3Uploaded byThinh
- ps2Uploaded byThinh
- ps1Uploaded byThinh
- Final SolUploaded byThinh
- exam2Uploaded byThinh
- exam1Uploaded byThinh
- exam1solUploaded byThinh
- 534 CoversUploaded byThinh
- Minimax OptimizationUploaded byThinh

- Decision TreeUploaded byratnams
- ase10bookUploaded byJohn BonJovi
- Correlation, Regression and Test of Signficance in RUploaded byprem
- The Use of the QUEST ProgramUploaded byMohanah Jayakumaran
- minitab spcUploaded byMahender Kumar
- Operations Management problems (Quality)Uploaded bygckodali
- SAS Code for Some Experimental DesignUploaded byWenping Hu
- ASSP8_Uploaded byfff9210
- Module 1 ProbabilityUploaded byUlina26
- Multinomial and ordinal logistic regression using PROC LOGISTICUploaded byfffresh
- RegressionUploaded byDebayanChakraborty
- Stat Chap009Uploaded byJoshz Tjoeng
- Stats Chap10Uploaded bySameh Salah
- Ch06Uploaded byliinddoss
- Qt-i(Prob Dist III)(6)Uploaded byPartha Boyal
- multple.docUploaded byHItesh Khurana
- Basic Econometrics Chapter 3 SolutionsUploaded bytariqmtch
- hw4_solUploaded byanthalya
- For 6520-Research II Final ReviewUploaded byrcolb18339
- DefinitionUploaded byAshis karmakar
- Standardised Regression Coefficient-metaanalysisUploaded byJasleen Kaur
- Lignin Jadi HoreUploaded byJoko Widhodho
- Simple RegressionUploaded byCarl Martin Engcoy
- section6_5Uploaded byChandrachuda Sharma
- selection documentUploaded byAbhishek Das
- fcdae.pdfUploaded bymusa
- Industrial Engineering by S K Mondal [Marinenotes.blogspot.com]Uploaded byAbilasha Vediappan
- Worthington and Higgs (2003)Uploaded byramoskathia
- ANOVA Computer OutputUploaded byBorad M. Barkachary
- New Microsoft Excel WorksheetUploaded bySabir Ali

## Much more than documents.

Discover everything Scribd has to offer, including books and audiobooks from major publishers.

Cancel anytime.