Applied Statistical Mechanics Lecture Note - 10
Basic Statistics and Monte-Carlo Method -2
고려대학교 화공생명공학과 강정원 Table of Contents
1. General Monte Carlo Method 2. Variance Reduction Techniques 3. Metropolis Monte Carlo Simulation 1.1 Introduction
Monte Carlo Method Any method that uses random numbers Random sampling the population Application • Science and engineering • Management and finance For given subject, various techniques and error analysis will be presented Subject : evaluation of definite integral
b I = ρ(x)dx a 1.1 Introduction
Monte Carlo method can be used to compute integral of any dimension d (d-fold integrals) Error comparison of d-fold integrals Simpson’s rule,… E ∝ N −1/ d − Monte Carlo method E ∝ N 1/ 2 purely statistical, not rely on the dimension !
Monte Carlo method WINS, when d >> 3 1.2 Hit-or-Miss Method
Evaluation of a definite integral
b I = ρ(x)dx a h X X X ≥ ρ X h (x) for any x X Probability that a random point reside inside X O the area O O I N' O O r = ≈ O O (b − a)h N a b
N : Total number of points N’ : points that reside inside the region N' I ≈ (b − a)h N 1.2 Hit-or-Miss Method
Start
Set N : large integer
N’ = 0 h X X X X X Choose a point x in [a,b] = − + X Loop x (b a)u1 a O N times O O y = hu O O Choose a point y in [0,h] 2 O O
a b if [x,y] reside inside then N’ = N’+1
I = (b-a) h (N’/N)
End 1.2 Hit-or-Miss Method
Error Analysis of the Hit-or-Miss Method It is important to know how accurate the result of simulations are The rule of 3σ’s Identifying Random Variable N = 1 X X n N n=1 From central mean theorem , X is normal variable in the limit of large N
each X n X mean value : μ mean value : μ variance : σ 2 variance : σ 2 / N 1.2 Hit-or-Miss Method
Sample Mean : estimation of actual mean value (μ) N μ = 1 ' xn N n=1 1 N N' μ = = = x01 ' xn r N = N n 1 p(x) r 1-r N = xn N' n=1
Accuracy of simulation the most probable error 0.6745σ σ = V (X ) N 1.2 Hit-or-Miss Method
Estimation of error
0.6745σ σ = V (X ) N
We do not know exact value of s , m We canσ also estimate the variance and the mean value from samples … 1 N '2 = (x − μ')2 − n N 1 n=1 1.2 Hit-or-Miss Method
For present problem (evaluation of integral) exact answer (I) is known estimation of error is,
V (X ) = E(X 2 ) − []E(X ) 2
E(X ) = xp(x) =1× r + 0×(1− r) = r = μ E(X 2 ) = x2 p(x) =1× r + 0×(1− r) = r
V (X ) = r − r 2 = (1− r)r = 2 σ = (1− r)r σ I = r(a − b)h = μ(a − b)h
0.6745σ r(1− r) I((b − a)h − I) I HM = = 0.6745×(b − a)h = 0.6745 error N N N 1.3 Sample Mean Method
ρ ρ ρ(x) is a continuous function in x and has a mean value ; b (x)dx 1 b < >= a = ρ(x)dx b ρ − a dx b a a b ∴I = (x)dx = (b − a) < ρ > a ρ N < >= 1 ρ (xn ) N n=1 = − + = xn (b a)un a un uniform random variable in [0,1] 1.3 Sample Mean Method
Error Analysis of Sample Mean Method Identifying random variable μ N =ρ 1 Y Yn N n=1 1 N 1 N =< >≈ y = ρ(x ) Y n n N n=1 N n=1 ρ ρ Variance N ρ < 2 >= 1 ρ 2 (xn ) 2 2 V ( ) =< > −[]< ρ > N n=1
V (x) I SM = 0.6745σ = (b − a)×0.6745 error N 1.3 Sample Mean Method
If we know the exact answer,
b L ρ(x)2 dx − I 2 I SM = 0.6745 a error N 1.3 Sample Mean Method
Start
Set N : large integer
s1 = 0, s2 = 0
Loop xn = (b-a) un + a N times ρ yn = (xn)
2 s1 = s1 + yn , s2 = s2 + yn
Estimate mean μ’=s /N SM V ' 1 I = (b − a)×0.6745 Estimate variance V’ = s /N – μ’2 error 2 N
End QUIZ
π Compare the error for the integral / 2 π I = sin xdx = − cos x / 2 =1 0 0
using HM and SM method
0.6745σ r(1− r) I((b − a)h − I) I HM = = 0.6745×(b − a)h = 0.6745 error N N N
b L ρ(x)2 dx − I 2 I SM = 0.6745 a error N Example : Comparison of HM and SM
π Evaluate the integral π / 2 π I = sin xdx = − cos x / 2 =1 0 0 I((b − a)h − I) 1(( / 2 − 0)×1−1) π / 2 −1 I HM = 0.6745 = 0.6745 = 0.6745 error N N N ρ< ρ >= I /(b − a) = 2 /π 1 π / 2 < 2 >= sin 2 xdx =1/ 2 − 0 ρ b a π 1 2 V ( ) = − 2 π 2 π V ' ( 2 / 4)(1/ 2 − 4 / 2 ) π 2 /8 −1 I SM = 0.6745(b − a) = 0.6745 = 0.6745 error N N N Example : Comparison of HM and SM
Comparison of error
π 2 SM −1 I error = 8 ≈ 0.64 SM method has 36 % less error than HM I HM π error −1 2
No of evaluation having the same error
π 2 −1 SM = 8 HM ≈ HM SM method is more than twice faster than HM N π N 0.41N −1 2 2.1 Variance Reduction Technique - Introduction
Monte Carlo Method and Sampling Distribution μ Monteμ Carlo Method : Take values from random sample From central limit theorem, σ 2 = = σ 2 / N μ 3s rule σ μ P( − 3 ≤ X ≤ − 3σ ) ≈ 0.9973
Most probable error 0.6745σ Error ≈ ± N Important characteristics Error ∝1/ N Error ∝ σ 2.1 Variance Reduction Technique - Introduction
Reducing error *100 samples reduces the error order of 10 Reducing variance Variance Reduction Technique
The value of variance is closely related to how samples are taken Unbiased sampling Biased sampling • More points are taken in important parts of the population 2.2 Motivation of Variance Reduction Technique
If we are using sample-mean Monte Carlo Method Variance depends very much on the behavior of ρ(x) ρ(x) varies little variance is small ρ(x) = const variance=0 Evaluation of a integralμ b − a N I'= (b − a) = ρ(x ) Y n N n=1 Near minimum points contribute less to the summation Near maximum points contribute more to the summation
More points are sampled near the peak ”importance sampling strategy” 2.3 Variance Reduction using Rejection Technique
Variance Reduction for Hit-or-Miss method In the domain [a,b] choose a comparison function
w(x) ≥ ρ(x) w(x) x ρ(x) X = X W (x) w(x)dx X −∞ X b X = O A w(x)dx O a O O O − Au = w(x) x = W 1(Au) O O a b Points are generated on the area under w(x) function Random variable that follows distribution w(x) 2.3 Variance Reduction using Rejection Technique
Points lying above ρ(x) is rejected N' I ≈ A N w(x) ρ(x) = X y w(x )u X n n n X X ≤ρ X 1 if yn (xn ) O q = O n > ρ O 0 if yn (xn ) O O O O
a b q10 = P(q) r 1-r r I / A 2.3 Variance Reduction using Rejection Technique
Error Analysis E(Q) = r, V (Q) = r(1− r) I = Ar = AE(Q)
− RJ ≈ I(A I) Hit or Miss method Ierror 0.67 N A = (b − a)h
Error reduction A → I then Error → 0 2.3 Variance Reduction using Rejection Technique
Start
Set N : large integer w(x) ρ(x) X X X N’ = 0 X X O 1 O Loop Generate u1, x= W- (Au1) O N times O O O O
Generate u2, y=u2 w(x) a b If y<= f(x) accept value N’ = N’+1 Else : reject value − RJ I'(A I') I = (b-a) h (N’/N) I ≈ 0.67 error N
End 2.4 Importance Sampling Method
Basic idea Put more points near maximum Put less points near minimum
F(x) : transformation function (or weight function_
x F(x) = f (x)dx −∞ y = F(x) x = F −1(y) 2.4 Importance Sampling Method
dy / dxρ= f (x) → dx = dy / f (x)
b (x) b ρ(x) I = dy = f (x)dx a a f (x) f (x) ρ(x) γ (x) = f (x) η < > = bη f (x) f (x)dx a
if we choose f(x) = cρ(x) ,then variance will be small The magnitude ofγ error depends on the choice of f(x)
= b =< γ > I (x) f (x)dx f a 2.4 Importance Sampling Method
Estimate of error γ N =< > ≈ 1 γ I f (xn ) N n=1
V (γ ) = f Ierror 0.67 γ N γ =< 2 > − < γ > 2 V f ( ) f ( f )
< γ 2 > −I 2 I IS = 0.67 f error N 2.4 Importance Sampling Method
Start
Set N : large integer
s1 = 0 , s2 = 0
Loop Generate xn according to f(x) N times γ ρ n = (xn) / f ( xn)
γ Add n to s1 γ Add n to s2 V ' 2 IS I ‘ =s1/N , V’=s2/N-I’ I = 0.67 error N
End 3. Metropolis Monte Carlo Method and Importance Sampling
Average of a property in Canonical Ensemble
A(r N )exp(−U (r N ) / kT)dr N < > = A NVT exp(−U (r N ) / kT)dr N exp(−U (r N ) / kT) = A(r N )dr N Z(r N ) = Ν (r N )A(r N )dr N
Probability 3. Metropolis Monte Carlo Method and Importance Sampling
N Create ni random points in a volume ri such that = N ni N (ri )L < > = 1 N A NVT ni A(r ) L trials
Problem : How we can generate ni random points N according to N (ri )?
We cannot use inversion method Use Markov chain with Metropolis algorithm 3. Metropolis Monte Carlo Method and Importance Sampling
Markov chain :Sequence of stochastic trials satisfies few some conditions Stochastic process that has no memory Selection of the next state only depends on current state, and not on prior state π Process is fully defined by a set of transition probabilities ij
π ij = probability of selecting state j next, given that presently in state i. Π π Transition-probability matrix collects all ij Markov Chain
Notation Outcome ρ Transition matrix π
Example Reliability of a computer • if it is running 60 % of running correctly on the next day • if it is down it has 80 % of down on the next day
0.6 0.4 = π 0.3 0.7 Markov Chain
ρ(1) = (0.5 0.5) ρ(2) = ρ(1)π = (0.45 0.55)
ρ(3) = ρ(2)π = ρ(1)π2 = (0.435 0.565)
τ (1) τ ρ = limρ π = (0.4286 0.5714) limiting behavior always converges to a certain value →∞ independent of initial condition ρ π ρπ = ρ = ρ m mn n m
π = Stochastic matrix : sum of the probability should be 1 mn 1 n
Features - Every state can be eventually reached from another state - The resulting behavior follows a certain probability