I hope this is the right place for such a basic question. I found this and this solutions quite articulated, hence they do not help me to get the fundamentals of the procedure.
Consider a random dataset:
x <- c(1.38, -0.24, 1.72, 2.25)
w <- c(3, 2, 4, 2)
How can I find the value of μ that minimizes the least squares equation :
The package manipulate allows to manually change with bar the model with different values of μ, but I am looking for a more precise procedure than "try manually until you do not find the best fit".
Note: If the question is not correctly posted, I would welcome constructive critics.
You could proceed as follows:
optim(mean(x), function(mu) sum(w * (x - mu)^2), method = "BFGS")$par
# [1] 1.367273
Here mean(x) is an initial guess for mu.
I'm not sure if this is what you want, but here's a little algebra:
We want to find mu to minimise
S = Sum{ i | w[i]*(x[i] - mu)*(x[i] - mu) }
Expand the square, and rearrange into three summations. bringing things that don't depend on i outside the sums:
S = Sum{i|w[i]*x[i]*x[i])-2*mu*Sum{i|w[i]*x[i]}+mu*mu*Sum{i|w[i]}
Define
W = Sum{i|w[i]}
m = Sum{i|w[i]*x[i]} / W
Q = Sum{i|w[i]*x[i]*x[i]}/W
Then
S = W*(Q -2*mu*m + mu*mu)
= W*( (mu-m)*(mu-m) + Q - m*m)
(The second step is 'completing the square', a simple but very useful technique).
In the final equation, since a square is always non-negative, the value of mu to minimise S is m.
Related
I'm reading Deep Learning by Goodfellow et al. and am trying to implement gradient descent as shown in Section 4.5 Example: Linear Least Squares. This is page 92 in the hard copy of the book.
The algorithm can be viewed in detail at https://www.deeplearningbook.org/contents/numerical.html with R implementation of linear least squares on page 94.
I've tried implementing in R, and the algorithm as implemented converges on a vector, but this vector does not seem to minimize the least squares function as required. Adding epsilon to the vector in question frequently produces a "minimum" less than the minimum outputted by my program.
options(digits = 15)
dim_square = 2 ### set dimension of square matrix
# Generate random vector, random matrix, and
set.seed(1234)
A = matrix(nrow = dim_square, ncol = dim_square, byrow = T, rlnorm(dim_square ^ 2)/10)
b = rep(rnorm(1), dim_square)
# having fixed A & B, select X randomly
x = rnorm(dim_square) # vector length of dim_square--supposed to be arbitrary
f = function(x, A, b){
total_vector = A %*% x + b # this is the function that we want to minimize
total = 0.5 * sum(abs(total_vector) ^ 2) # L2 norm squared
return(total)
}
f(x,A,b)
# how close do we want to get?
epsilon = 0.1
delta = 0.01
value = (t(A) %*% A) %*% x - t(A) %*% b
L2_norm = (sum(abs(value) ^ 2)) ^ 0.5
steps = vector()
while(L2_norm > delta){
x = x - epsilon * value
value = (t(A) %*% A) %*% x - t(A) %*% b
L2_norm = (sum(abs(value) ^ 2)) ^ 0.5
print(L2_norm)
}
minimum = f(x, A, b)
minimum
minimum_minus = f(x - 0.5*epsilon, A, b)
minimum_minus # less than the minimum found by gradient descent! Why?
On page 94 of the pdf appearing at https://www.deeplearningbook.org/contents/numerical.html
I am trying to find the values of the vector x such that f(x) is minimized. However, as demonstrated by the minimum in my code, and minimum_minus, minimum is not the actual minimum, as it exceeds minimum minus.
Any idea what the problem might be?
Original Problem
Finding the value of x such that the quantity Ax - b is minimized is equivalent to finding the value of x such that Ax - b = 0, or x = (A^-1)*b. This is because the L2 norm is the euclidean norm, more commonly known as the distance formula. By definition, distance cannot be negative, making its minimum identically zero.
This algorithm, as implemented, actually comes quite close to estimating x. However, because of recursive subtraction and rounding one quickly runs into the problem of underflow, resulting in massive oscillation, below:
Value of L2 Norm as a function of step size
Above algorithm vs. solve function in R
Above we have the results of A %% x followed by A %% min_x, with x estimated by the implemented algorithm and min_x estimated by the solve function in R.
The problem of underflow, well known to those familiar with numerical analysis, is probably best tackled by the programmers of lower-level libraries best equipped to tackle it.
To summarize, the algorithm appears to work as implemented. Important to note, however, is that not every function will have a minimum (think of a straight line), and also be aware that this algorithm should only be able to find a local, as opposed to a global minimum.
Let g(x) = 1/(2*pi) exp ( - x^2 / 2) be the density of the normal distribution with mean 0 and standard deviation 1. In some calculation on paper appeared integrals of the form
where c>0 is a positive number.
Since I could not evaluate this by hand, I had the idea to approximate and plot it. I tried this in R, because R provides the dnorm function and a function to do integrals.
You see that I need to integrate numerically n times, where n shall be chosed by the call of a plot function. My code has an for-loop to create those "incomplete" convolutions iterativly.
For example even with n=3 and c=1 this gives me an error. n=2 (thus it's one integration) works.
N = 3
ngauss <- function(x) dnorm(x , mean = 0, sd = 1)
convoluts <- list()
convoluts[[1]] <- ngauss
for (i in 2:N) {
h <- function(y) {
g <- function(z) {ngauss(y-z)*convoluts[[i-1]](z)}
return(integrate(g, lower = -1, upper = 1)$value)
}
h <- Vectorize(h)
convoluts[[i]] <- h
}
convoluts[[3]](0)
What I get is:
Error: evaluation nested too deeply: infinite recursion /
options(expressions=)?
I understand that this is a hard computation, but for "small" n something similar should possible.
Maybe someone can help me to fix my code or provide a recommendation how I can implement this in a better way. Another language that is more appropriate for this would be also okay.
The issue appears to be in how integrate deals with variables in different environments. In particular, it doesn't really deal with i correctly in each iteration. Instead using
h <- evalq(function(y) {
g <- function(z) {ngauss(y - z) * convoluts[[i - 1]](z)}
integrate(g, lower = -1, upper = 1)$value
}, list(i = i))
does the job and, say, setting N <- 6 quickly gives
convoluts[[N]](0)
# [1] 0.03423872
As your integration is simply the pdf of a sum of N independent standard normals (which then follows N(0, N)), we may also verify this approach by setting lower = -Inf and upper = Inf. Then with N <- 4 we have
dnorm(0, sd = sqrt(N))
# [1] 0.1994711
convoluts[[N]](0)
# [1] 0.1994711
So, for practical purposes, when c = Inf, you are way better off using dnorm rather than manual computations.
I am trying to solve the following optimization problem using cvxpy:
x and delta_x are (1,N) row vectors. A is a (N,N) symmetric matrix and b is a scalar. I am trying to find a y, such that it minimizes the sum of squares of (y - delta_x) with the constraint (x+y).A.(x+y).T - b = 0. Below is my attempt to solve it.
x = np.reshape(np.ravel(x_data.T), (1, -1))
delta_x = np.reshape(np.ravel(delta.T), (1, -1))
y = cp.Variable(delta_x.shape)
objective = cp.Minimize(cp.sum_squares(y - delta_x))
constraints = [cp.matmul(cp.matmul(x + y, A), (x + y).T) == (b*b)]
prob = cp.Problem(objective, constraints)
result = prob.solve()
I keep getting the error 'cvxpy.error.DCPError: Problem does not follow DCP rules'.
I followed the rules stated in the answer here, but I don't understand how to construct the proper cvxpy minimization Problem. Any help would be greatly appreciated.
Thanks!
I have written the code below for minimization of error by changing the value of alpha (using iteration method).
set.seed(16)
npoints = 10000
Y = round(runif(npoints), 3)
OY = sample(c(0, 1, 0.5), npoints, replace = T)
minimizeAlpha = function(Y, OY, alpha) {
PY = alpha*Y
error = OY - PY
squaredError = sapply(error, function(x) x*x)
sse = sum(squaredError)
return(sse)
}
# # Iterate for 10000 values
alphas = seq(0.0001, 1, 0.0001)
sse = sapply(alphas, function(x) minimizeAlpha(Y, OY, x))
print(alphas[sse == min(sse)])
I have used sapply for basic optimization. But, if the number of points are more than 10000 this code is running forever. So, is there any better way of implementation or any standard techniques to optimize (like Bisection). If so can you please help me in optimizing the code.
Note: I need the value of alpha with at least 4 decimals.
Any help is appreciated.
Replacing sapply instead of for isn’t more efficient, that’s a misconception. It’s merely often simpler code.
However, you can actually take advantage of vectorisation in your code — and that would be faster.
For instance, sapply(error, function(x) x*x) can simply be replaced by x * x. The sum of squared errors of numbers in R is thus simply sum((OY - PY) ** 2).
Your whole function thus boils down to:
minimizeAlpha = function(Y, OY, alpha)
sum((OY - alpha * Y) ** 2)
This should be more efficient — but first and foremost it’s better code and more readable.
I have a functional like this :
(LaTex formula: $v[y]=\int_0^2 (y'^2+23yy'+12y^2+3ye^{2t})dt$)
with given start and end conditions y(0)=-1, y(2)=18.
How can I find extreme values of this functional in R? I realize how it can be done for example in Excel but didn't find appropriate solution in R.
Before trying to solve such a task in a numerical setting, it might be better to lean back and think about it for a moment.
This is a problem typically treated in the mathematical discipline of "variational calculus". A necessary condition for a function y(t) to be an extremum of the functional (ie. the integral) is the so-called Euler-Lagrange equation, see
Calculus of Variations at Wolfram Mathworld.
Applying it to f(t, y, y') as the integrand in your request, I get (please check, I can easily have made a mistake)
y'' - 12*y + 3/2*exp(2*t) = 0
You can go now and find a symbolic solution for this differential equation (with the help of a textbook, or some CAS), or solve it numerically with the help of an R package such as 'deSolve'.
PS: Solving this as an optimization problem based on discretization is possible, but may lead you on a long and stony road. I remember solving the "brachistochrone problem" to a satisfactory accuracy only by applying several hundred variables (not in R).
Here is a numerical solution in R. First the functional:
f<-function(y,t=head(seq(0,2,len=length(y)),-1)){
len<-length(y)-1
dy<-diff(y)*len/2
y0<-(head(y,-1)+y[-1])/2
2*sum(dy^2+23*y0*dy+12*y0^2+3*y0*exp(2*t))/len
}
Now the function that does the actual optimization. The best results I got were using the BFGS optimization method, and parametrizing using dy rather than y:
findMinY<-function(points=100, ## number of points of evaluation
boundary=c(-1,18), ## boundary values
y0=NULL, ## optional initial value
method="Nelder-Mead", ## optimization method
dff=T) ## if TRUE, optimizes based on dy rather than y
{
t<-head(seq(0,2,len=points),-1)
if(is.null(y0) || length(y0)!=points)
y0<-seq(boundary[1],boundary[2],len=points)
if(dff)
y0<-diff(y0)
else
y0<-y0[-1]
y0<-head(y0,-1)
ff<-function(z){
if(dff)
y<-c(cumsum(c(boundary[1],z)),boundary[2])
else
y<-c(boundary[1],z,boundary[2])
f(y,t)
}
res<-optim(y0,ff,control=list(maxit=1e9),method=method)
cat("Iterations:",res$counts,"\n")
ymin<-res$par
if(dff)
c(cumsum(c(boundary[1],ymin)),boundary[2])
else
c(boundary[1],ymin,boundary[2])
}
With 500 points of evaluation, it only takes a few seconds with BFGS:
> system.time(yy<-findMinY(500,method="BFGS"))
Iterations: 90 18
user system elapsed
2.696 0.000 2.703
The resulting function looks like this:
plot(seq(0,2,len=length(yy)),yy,type='l')
And now a solution that numerically integrates the Euler equation.
As #HansWerner pointed out, this problem boils down to applying the Euler-Lagrange equation to the integrand in OP's question, and then solving that differential equation, either analytically or numerically. In this case the relevant ODE is
y'' - 12*y = 3/2*exp(2*t)
subject to:
y(0) = -1
y(2) = 18
So this is a boundary value problem, best approached using bvpcol(...) in package bvpSolve.
library(bvpSolve)
F <- function(t, y.in, pars){
dy <- y.in[2]
d2y <- 12*y.in[1] + 1.5*exp(2*t)
return(list(c(dy,d2y)))
}
init <- c(-1,NA)
end <- c(18,NA)
t <- seq(0, 2, by = 0.01)
sol <- bvpcol(yini = init, yend = end, x = t, func = F)
y = function(t){ # analytic solution...
b <- sqrt(12)
a <- 1.5/(4-b*b)
u <- exp(2*b)
C1 <- ((18*u + 1) - a*(exp(4)*u-1))/(u*u - 1)
C2 <- -1 - a - C1
return(a*exp(2*t) + C1*exp(b*t) + C2*exp(-b*t))
}
par(mfrow=c(1,2))
plot(t,y(t), type="l", xlim=c(0,2),ylim=c(-1,18), col="red", main="Analytical Solution")
plot(sol[,1],sol[,2], type="l", xlim=c(0,2),ylim=c(-1,18), xlab="t", ylab="y(t)", main="Numerical Solution")
It turns out that in this very simple example, there is an analytical solution:
y(t) = a * exp(2*t) + C1 * exp(sqrt(12)*t) + C2 * exp(-sqrt(12)*t)
where a = -3/16 and C1 and C2 are determined to satisfy the boundary conditions. As the plots show, the numerical and analytic solution agree completely, and also agree with the solution provided by #mrip