Questions tagged [monte-carlo]
Questions on Monte Carlo methods, methods that require the repeated generation of pseudo- or quasi-random numbers for computing their results.
705
questions
0
votes
0
answers
15
views
Is the sample path from Monte Carlo Simulation follows CLT?
I'm pricing some derivative securities with Monte Carlo Simulation.
I don't know population follows which distribution.
But When I some calculation with my samples(all the each path) ,for example $X = ...
- 53
0
votes
0
answers
45
views
Monte Carlo simulation at football
Would you please help and clarify how to run a Monte Carlo simulation to determine the probability of one of the two teams winning a match given the average number of goals for each team (in matches ...
1
vote
1
answer
24
views
Monte Carlo estimation of this probability
Let $p=P(X+Y\geq t)$ and $t\in \Bbb R$.
Question: Using the classic Monte Carlo method, find an estimator $p_n$ of $p$ using $F^{-1}_X$ and $F^{-1}_Y$
Attempt: I defined $$Z=X+Y$$ then I expressed $$p=...
- 271
0
votes
1
answer
46
views
Monte Carlo computation of probability of a subset of samples
I would like to compute the probability for some subset $\omega \subset \Omega$ of events to occur, i.e. $P(\omega) = \sum_{x \in \omega} P(x)$ where I know $P(x)$ for all $x \in \Omega$, which are ...
- 175
0
votes
0
answers
26
views
Why does this plotted data dip before rising?
The red plot shows the amount of total time spent waiting at a given trade frequency. The data was generated by continually letting an asset price go up and down randomly, then repeatedly waiting for ...
- 11
2
votes
0
answers
19
views
Expected Value of Slot Machine
I have a probability question that has to do with slot machines. Here is how the game works:
There are two reels, one on the left and one on the right. There are several symbols on each reel, one of ...
- 79
1
vote
1
answer
26
views
Probability of a point sampled from a ball lying in a spherical cap/segment
What is the probability that a point sampled from an n-ball lies in a spherical segment in the ball?
Alternatively, what is the probability that a point sampled from an n-ball lies in a spherical cap ...
- 121
2
votes
1
answer
110
views
Importance Sampling: What is the role of the target distribution $p(x)$ in Monte Carlo integration?
I am currently implementing a few different approaches to Monte Carlo Integration and there is a conceptual hurdle that I don’t fully understand yet.
The notation varies from one source to another, ...
- 73
0
votes
0
answers
34
views
Volume of a spherical segment in high dimensions
Consider 2 parallel hyperplanes of the type
$0 \leq \langle w,x \rangle + b$ and $\langle w,x \rangle + b < c$ where $x, w \in \mathbb{R}^n ; b,c \in \mathbb{R}$
cutting an $n$-ball with radius $r$ ...
- 121
1
vote
1
answer
29
views
Metropolis-Hastings : Finding the transition matrix given the state space and the stationary distribution
In this paper Diaconis, P. (2009). The markov chain monte carlo revolution. Bulletin of the American Mathematical Society, 46(2), 179-205. https://math.uchicago.edu/~shmuel/Network-course-readings/...
- 56
0
votes
0
answers
40
views
How to use Monte Carlo method to calculate the volume of a cone inscribed in the unit cube?
unit cube L=1
how do i use random numbers with monte carlo method to calculate the volume of this cone?
if anyone can use matlab to solve it, i appreciate it!
- 1
0
votes
0
answers
33
views
Modeling dependent events
Say we have event A (saving a life) and event B (person living after initially getting saved). A and B are dependent events as p(A|B) = 1. I want to model the probability of a person living which is p(...
- 1
1
vote
1
answer
35
views
What is the probability that a Markov chain transitions between states if it passes through a specified intermediate transition?
Consider a discrete-time finite Markov chain with transition probability matrix $P$. One of the foundational results of Markov theory is, of course, that the probability that the chain transitions ...
- 5,401
0
votes
0
answers
15
views
Metropolis-Hastings algorithm Hastings ratio
This question is probably elementary, but it is not obvious to me how to compute the Hastings ratio since there is p in it which is the very target distribution we would like to find.
- 217
0
votes
1
answer
25
views
Box-Muller Transformation: Polar Coordinates Interpretation
I am aware that the Box-Muller transform leverages polar coordinates to arrive at the final transformations by plotting two uniform random variables, $(u, v)$ in the Cartesian plane. I have not seen ...
3
votes
0
answers
38
views
Does there exist a uniform Monte-Carlo Approximation of certain function classes?
Given a measurable and bounded function $f:X \to \mathbb{R}$ on a metric-measure space $(X, d, \mathcal{P})$, we can approximate $\int_\chi f$ in terms of $N$ iid samples $X_1, \ldots, X_N \sim \...
- 167
1
vote
0
answers
38
views
Estimate of Expectation of Estimated Function
Let $X_1,X_2,...$ be a sequence of random values distributed uniformly in $[0,1]$. By the law of large numbers, we have for any integrable function $f=f(x)$ (convergence in probability to an ...
- 11
1
vote
0
answers
33
views
Monte Carlo integration - Intuition
I am studying engineering and I am learning about the Monte Carlo integration which I find a bit hard to grasp the maths. I have watched a few videos and read some other notes and I feel I understand ...
- 77
1
vote
0
answers
36
views
Convergence of a type of Monte Carlo integration which is different from the common one
$a_i \in (0,1)$, $I = 1,\cdots,N$ are $N$ random samples from uniform distribution $U(0,1)$. $a_i$ is in ascending order $a_1 < a_2 < \cdots < a_N$.
$Q(p)$, $p\in(0,1)$ is a differentiable ...
- 133
1
vote
0
answers
16
views
Singular Value Decomposition (SVD) with Monotonic Constraint
I am trying to compress some cumulative distribution functions (CDFs) which are stored in an $N \times M$ matrix $A$. Each of the $M$ columns contains $N$ monotonically-increasing values which might ...
- 15
0
votes
0
answers
15
views
Monte Carlo conditional variance reduction
On this lecture at page 9: https://home.csulb.edu/~tebert/teaching/lectures/552/vr/vr.pdf
you can found:
$$\operatorname{Var}\left(1-U^{1 / 2}\right)=E\left[\left(1-U^{2}\right)\right]-\left(\frac{\pi}...
- 71
0
votes
0
answers
80
views
Monte Carlo Tree Search
You are to manually run the MCTS algo-
rithm for the navigation example covered in class for 10
iterations. For this, you will need simulation results for
nodes at tree depth up to 2, which is ...
- 23
1
vote
0
answers
53
views
Finding Monte Carlo estimate $\hat{K}$ using Monte Carlo integration
Let
$$f\left(x\right)=K\left[sin^2\left(6x\right)+3cos^2\left(x\right)sin^2\left(4x\right)+1\right]e^{-\frac{x^2}{2}},\:-\infty <x<\infty $$
be the probability density function of a random ...
- 31
0
votes
0
answers
14
views
Partition in Gibbs Sampling; obtaining the conditional Posterior Distribution
I would like to know the conditional posterior distribution if the following equation is partitioned by the unknowns by $ [\mu, \sigma^{2}]$ and $x_{1}$ of the equation:
$$
\begin{aligned}
g\left(\mu,...
- 1
0
votes
0
answers
19
views
Proof of convergence for the Monte-Carlo method in the Linear Transport Equation
There exists a well known procedure for simulating the transport equation using the Monte Carlo (MC) approach. I want to understand the mathematical connection (not physical) of this approach to the ...
- 1,579
3
votes
1
answer
80
views
Feynman-Kac proof
I have seen numerous proofs, showing that if $u\left(x,t\right)$ satisfies a PDE of the form:
$$\frac{\partial u}{\partial t}+\mu\left(x,t\right) \frac{\partial u}{\partial x}+\frac{1}{2}{\left(\sigma\...
- 1,579
2
votes
0
answers
76
views
quasi-Newton methods with Monte Carlo sampling
I have an optimisation problem of the form $$\text{argmax}_{\theta} \ L(\theta),$$
where
$$L(\theta) = \ \mathbb{E}_{X\sim p(\cdot)}\left[f(X,\theta)\right],$$
and where $p(\cdot)$ is a distribution ...
- 183
0
votes
0
answers
12
views
Does Metropolis-Hastings make sence if I have the normalizing constant of $p(x)$?
I have $x \sim N(\mu, diag(\sigma))$ and a non-trivial function $y = f(x)$ which transforms the distribution.
I want to approximate the distribution of $y$ by a normal distribution and thought the ...
- 105
0
votes
0
answers
24
views
Training neural networks | Monte Carlo Methods
Assume that we have a dataset D = {(x_1, y_1), ... , (x_n, y_n)}.
We want to train a neural network and update the weights with gradients computed on every mini-batch.
If we shuffle our mini-batches ...
0
votes
0
answers
50
views
How is Simulated Annealing an "Adaptation of The Metropolis-Hastings Algorithm"?
I'm trying to understand how simulated annealing is related to the Metropolis-Hastings algorithm, that is, if they are at all. The Wikipedia page states that simulated annealing "is an adaptation ...
0
votes
0
answers
18
views
Conditional Variance Implementation, Integral approximation with Monte Carlo
as part of my master's thesis, I have to implement the following conditional variance
\begin{align*}
\mathbb{V}ar[\hat{v}|\hat{y}] &= \mathbb{E}\left[\hat{v}^{2} \mid \hat{y}\right] - \mathbb{E}\...
- 1
5
votes
1
answer
170
views
Finding the approximate value of improper integral using the Monte-Carlo method
Find the approximate value of the improper integral
$$
\int_{-3}^{\infty} \left( \int_{0.5}^{\infty} \frac{2+\sin(x+y)}{e^{0.4x}+0.4y^2} \,dx \right) \, dy
$$
using the Monte-Carlo method.
I have ...
- 165
0
votes
0
answers
52
views
Intuition behind using random variables in Monte Carlo methods / localization
I am trying to get a better intuitive understanding of why Monte Carlo works so well in approximating a solution to complex problems, such as calculating irrational numbers or the Particle Filter / ...
- 641
3
votes
1
answer
46
views
$f(X) = \mathbb{E}[Y|X]$ maximizes correlation coefficient $Cor(Y,f(X))$?
Given two random variables $X$ and $Y$, I want to find a function $f(\cdot)$ such that the correlation coefficient $Cor(Y,f(X)) = \frac{Cov(Y,f(X))}{Std(Y)Std(f(X))}$ is maximized. Intuitively, such $...
- 1,501
0
votes
0
answers
17
views
The question of standard deviation in gap statistics
From the paper of gap statistics, $\text { we estimate } E_{n}^{*}\left\{\log \left(W_{k}\right)\right\} \text { by an average of } B \text { copies } \log \left(W_{k}^{*}\right)$, $sd(k)$ is the ...
3
votes
0
answers
54
views
Construction of Markov Chain
Let's consider a toy example of applying a Markov Chain Monte Carlo (MCMC) method. Let $X$ be a discrete random variable whose unnormalized probability mass function is
$$
\tilde{p}(X=1)=4, \tilde{p}(...
- 860
0
votes
0
answers
25
views
Prove the existence of limiting distribution in MCMC.
I know the MCMC can produce a Markov chain with desired stationary distribution, which can be proved from the Detailed Balance Condition πiP_ij=πjP_ji.
But I don't know how to ensure the existence of ...
0
votes
1
answer
26
views
Multivariate control variate technique
In the control variate technique, one tries to improve convergence of the expected value of a random variable $X$, estimated from simulating a range of $n$ Monte Carlo simulations. This is done by ...
- 151
2
votes
1
answer
144
views
Understanding the Metropolis-Hastings Algorithm
Can someone please tell me if I have correctly written the code for MCMC Sampling (Metropolis Hastings Algorithm)?
Given a multivariate joint probability distribution function, I am interested in ...
- 1,688
0
votes
1
answer
78
views
An explanation for drift in diffusion processes in terms of probability distributions?
Consider the following Python implementation of an empirical experiment involving a diffusion processes.
...
- 147
3
votes
0
answers
128
views
monte-carlo gone wrong
Can someone give examples where defective pseudo-random number generators gave incorrect simulation (or sampling, or polling, or gaming, …) results?
I am aware of the RANDU debacle and of
Ferrenberg, ...
- 57
0
votes
0
answers
29
views
Producing direction unit vectors from 2D angle Gaussian distribution
I am trying to use the model given in the paper:
Representation of a Gaussian beam by rays
https://aapt.scitation.org/doi/10.1119/1.2201857
The model says that initial ray positions are normally ...
- 53
0
votes
0
answers
42
views
Choosing m, with replacement, from n, with a probability twist
I need to be able to answer questions like the one shown below. I believe this is related to the Monte-Carlo simulation:
A set holds integers $1$ to $1000.$ How many must I randomly choose, with ...
- 143
-1
votes
1
answer
42
views
Laplace transform / gaussian random variable
We have a gaussian random variable $X \sim N(0, \sigma^{2})$, with $\sigma^{2}$ unknown.
the Laplace transform given by:
$\phi(t) := \mathbb{E} [e^{tX}]$ = $e^{{\sigma}^{2} t^2/2}$
I need to make i.i....
- 119
1
vote
0
answers
58
views
Monte Carlo for estimating small
Suppose that I have two samples $x_1,\cdots,x_n$ and $y_1,\cdots, y_m$ of two random variables $X$ and $Y$, with $m$ and $n$ very large. I want to estimate the probability $P(Y>X)$ which I know is ...
- 136
2
votes
0
answers
62
views
Numerical Integration of a high dimensional function
My problem is the following, I have a function, with an input vector of $\mathbb{R^{3072}}$, which outputs {$\mathbb{ x \in R : 0 \leq x \leq 1}$}. I want to find the integral of the function over the ...
- 21
0
votes
0
answers
21
views
Simple Monte-Carlo results
In a formula where R= (w1X1+w2X2) * (W3X3+ W4X4) and 0<=w<=1, 0<=X<=10
I want to use Monte-Carlo to generate results.
I am setting the formula in excel, where cells containing W,X are ...
- 1
0
votes
0
answers
36
views
Monte Carlo and Importance Sampling
So I am messing around with Monte Carlo Integration and trying to reduce variance thru Importance Sampling.
The Monte Carlo I am considering is:
$$ F^N = \displaystyle \frac{1}{N} \sum_{i=1}^{N}\frac{...
- 11
1
vote
1
answer
73
views
Balls into bins with left and right bins always empty
N balls are sequentially and randomly allocated into M bins arranged in a circle. If a bin receives a ball, its left and right bins cannot receive any ball and are always set to be empty (new coming ...
- 11
1
vote
0
answers
45
views
Easier proof for existence of equilibrium distribution of markov chain
My goal is to get a firm theoretical foundation for the Metropolis-Hastings algorithm and the Gibbs sampler, but none of my classes or books I have found have covered this.
I found this paper titled ...
- 395