torch precision causes sum to ignore small float - pytorch

I am encountering an unexpected from pytorch where the sum ignores a 1e-6 number :
test_tensor = torch.tensor([10, 20, 10, 1e-6])
print(torch.sum(test_tensor) == torch.sum(test_tensor[0:-1]))
and the output is :
tensor(True)
this is troublesome for me as I need the difference between the two tensors to be none zero (strictly positive)
Is there a way to fix this issue.

Related

why is np.exp(x) not equal to np.exp(1)**x

Why is why is np.exp(x) not equal to np.exp(1)**x?
For example:
np.exp(400)
>>>5.221469689764144e+173
np.exp(1)**400
>>>5.221469689764033e+173
np.exp(400)-np.exp(1)**400
>>>1.1093513018771065e+160
This is optimisation of numpy that raise this diff.
Indeed, you have to understand how is calculated the Euler number in math:
e = (1/n)**n with n == inf.
I think numpy stop at a certain order:
You have in the numpy exp documentation here that is not very clear about how the Euler number is calculated.
Because of this order that is not equal to infinity, you have this small difference in the two calculations.
Indeed the value np.exp(400) is calculated using this: (1 + 400/n)**n
>>> (1 + 400/n)**n
5.221642085428121e+173
>>> numpy.exp(400)
5.221469689764144e+173
Here you have n = 1000000000000 wich is very small and raise this difference at 10e-5.
Indeed there is no exact value of the Euler number. Like Pi, you can only have an approched value.
It looks like a rounding issue. In the first case it's internally using a very precise value of e, while in the second you get a less precise value, which when multiplied 400 times the precision issues become more apparent.
The actual result when using the Windows calculator is 5.2214696897641439505887630066496e+173, so you can see your first outcome is fine, while the second is not.
5.2214696897641439505887630066496e+173 // calculator
5.221469689764144e+173 // exp(400)
5.221469689764033e+173 // exp(1)**400
Starting from your result, it looks it's using a value with 15 digits of precision.
2.7182818284590452353602874713527 // e
2.7182818284590450909589085441968 // 400th root of the 2nd result

Multivariable function local minimum using SciPy

Consider the function:
def f(x,y):
return x + 3*exp(y**2)
I was wondering, is it possible to use SciPy.optimize.minimize
to find the minimum value on say [0,1] (the unit interval) (for both, x and y)?
Here is my attempt:
bound = (0,1)
bds = [bound,bound]
x_0 = [0,0] (initial guess)
And thus,
scipy.optimize.minimize(f,x_0,method='SLSQP', \ bounds = bds)
But this isn't working.
I keep getting:
"unexpected character after line continuation character" At \ bounds = bnds
Note that I want my x and y to vary over the real numbers on [0,1]
Edit:
def f(x):
return x[0] + 3*exp(x[1]**2)
bound = (0,1)
bds = [bound,bound]
x_0 = [0,0] (initial guess)
scipy.optimize.minimize(f,x_0,method='SLSQP', bounds = bds)
Is this minimise function looking at only integer values 0 and 1? or is it looking at all real numbers in [0,1] (the unit interval?). If its the first, im not sure how to make it to the second how do I do so?
Your original code wouldn't work because
""unexpected character after line continuation character" At \ bounds = bnds":
is telling you that the "line continuation character" (the backslash) is causing a problem. You can't have anything after that character. Insert a line break after the backslash, or remove the backslash altogether
Once you fix that, you'll get an error saying
TypeError: f() missing 1 required positional argument: 'y'
This is because minimize wants a function that takes one input (read the "Parameters: fun part of the documentation). That input can be an array of shape (n, ). When you want a multivariate minimization, all n variables go into that single argument to your function
Re: "Is this minimise function looking at only integer values 0 and 1? or is it looking at all real numbers in [0,1] (the unit interval?). If its the first, im not sure how to make it to the second."
It would be a pretty useless optimizer if it only checked the values at the bounds, don't you think?
This is easy enough to check though! Your current function has a minimum at [0, 0], so it's not a great way to test what the function does. Let's define a function that has a minimum at a different number. For example, let's define a function that has a minimum at [0.5, 0.5]
def f(X):
return abs(X[0] - 0.5) * abs(X[1] - 0.5)
Running your code gives the result:
fun: 0.0
jac: array([0., 0.])
message: 'Optimization terminated successfully.'
nfev: 8
nit: 2
njev: 2
status: 0
success: True
x: array([0.5, 0.5])
which makes it pretty clear that minimize() looks in the entire interval.
It doesn't really look at all real numbers in the interval though (that would be impossible, given that there are infinite real numbers in any interval). Instead, it uses the optimization algorithms that you specify in the method argument.
The optimization result represented as a OptimizeResult object. Important attributes are: x the solution array, success a Boolean flag indicating if the optimizer exited successfully and message which describes the cause of the termination.

Change the precision of torch.sigmoid?

I want my sigmoid to never print a solid 1 or 0, but to actually print the exact value
i tried using
torch.set_printoptions(precision=20)
but it didn't work. here's a sample output of the sigmoid function :
before sigmoid : tensor([[21.2955703735]])
after sigmoid : tensor([[1.]])
but i don't want it to print 1, i want it to print the exact number, how can i force this?
The difference between 1 and the exact value of sigmoid(21.2955703735) is on the order of 5e-10, which is significantly less than machine epsilon for float32 (which is about 1.19e-7). Therefore 1.0 is the best approximation that can be achieved with the default precision. You can cast your tensor to a float64 (AKA double precision) tensor to get a more precise estimate.
torch.set_printoptions(precision=20)
x = torch.tensor([21.2955703735])
result = torch.sigmoid(x.to(dtype=torch.float64))
print(result)
which results in
tensor([0.99999999943577644324], dtype=torch.float64)
Keep in mind that even with 64-bit floating point computation this is only accurate to about 6 digits past the last 9 (and will be even less precise for larger sigmoid inputs). A better way to represent numbers very close to one is to directly compute the difference between 1 and the value. In this case 1 - sigmoid(x) which is equivalent to 1 / (1 + exp(x)) or sigmoid(-x). For example,
x = torch.tensor([21.2955703735])
delta = torch.sigmoid(-x.to(dtype=torch.float64))
print(f'sigmoid({x.item()}) = 1 - {delta.item()}')
results in
sigmoid(21.295570373535156) = 1 - 5.642236648842976e-10
and is a more accurate representation of your desired result (though still not exact).

Very large float in python

I'm trying to construct a neural network for the Mnist database. When computing the softmax function I receive an error to the same ends as "you can't store a float that size"
code is as follows:
def softmax(vector): # REQUIRES a unidimensional numpy array
adjustedVals = [0] * len(vector)
totalExp = np.exp(vector)
print("totalExp equals")
print(totalExp)
totalSum = totalExp.sum()
for i in range(len(vector)):
adjustedVals[i] = (np.exp(vector[i])) / totalSum
return adjustedVals # this throws back an error sometimes?!?!
After inspection, most recommend using the decimal module. However when I've messed around with the values being used in the command line with this module, that is:
from decimal import Decimal
import math
test = Decimal(math.exp(720))
I receive a similar error for any values which are math.exp(>709).
OverflowError: (34, 'Numerical result out of range')
My conclusion is that even decimal cannot handle this number. Does anyone know of another method I could use to represent these very large floats.
There is a technique which makes the softmax function more feasible computationally for a certain kind of value distribution in your vector. Namely, you can subtract the maximum value in the vector (let's call it x_max) from each of its elements. If you recall the softmax formula, such operation doesn't affect the outcome as it reduced to multiplication of the result by e^(x_max) / e^(x_max) = 1. This way the highest intermediate value you get is e^(x_max - x_max) = 1 so you avoid the overflow.
For additional explanation I recommend the following article: https://nolanbconaway.github.io/blog/2017/softmax-numpy
With a value above 709 the function 'math.exp' exceeds the floating point range and throws this overflow error.
If, instead of math.exp, you use numpy.exp for such large exponents you will see that it evaluates to the special value inf (infinity).
All this apart, I wonder why you would want to produce such a big number (not sure you are aware how big it is. Just to give you an idea, the number of atoms in the universe is estimated to be in the range of 10 to the power of 80. The number you are trying to produce is MUCH larger than that).

Spark : regression model threshold and precision

I have logistic regression mode, where I explicitly set the threshold to 0.5.
model.setThreshold(0.5)
I train the model and then I want to get basic stats -- precision, recall etc.
This is what I do when I evaluate the model:
val metrics = new BinaryClassificationMetrics(predictionAndLabels)
val precision = metrics.precisionByThreshold
precision.foreach { case (t, p) =>
println(s"Threshold is: $t, Precision is: $p")
}
I get results with only 0.0 and 1.0 as values of threshold and 0.5 is completely ignored.
Here is the output of the above loop:
Threshold is: 1.0, Precision is: 0.8571428571428571
Threshold is: 0.0, Precision is: 0.3005181347150259
When I call metrics.thresholds() it also returns only two values, 0.0 and 1.0.
How do I get the precision and recall values with threshold as 0.5?
You need to clear the model threshold before you make predictions. Clearing threshold makes your predictions return a score and not the classified label. If not you will only have two thresholds, i.e. your labels 0.0 and 1.0.
model.clearThreshold()
A tuple from predictionsAndLabels should look like (0.6753421,1.0) and not (1.0,1.0)
Take a look at https://github.com/apache/spark/blob/master/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassificationMetricsExample.scala
You probably still want to set numBins to control the number of points if the input is large.
I think what happens is that all the predictions are 0.0 or 1.0. Then the intermediate threshold values make no difference.
Consider the numBins argument of BinaryClassificationMetrics:
numBins:
if greater than 0, then the curves (ROC curve, PR curve) computed internally will be down-sampled to this many "bins". If 0, no down-sampling will occur. This is useful because the curve contains a point for each distinct score in the input, and this could be as large as the input itself -- millions of points or more, when thousands may be entirely sufficient to summarize the curve. After down-sampling, the curves will instead be made of approximately numBins points instead. Points are made from bins of equal numbers of consecutive points. The size of each bin is floor(scoreAndLabels.count() / numBins), which means the resulting number of bins may not exactly equal numBins. The last bin in each partition may be smaller as a result, meaning there may be an extra sample at partition boundaries.
So if you don't set numBins, then precision will be calculated at all the different prediction values. In your case this seems to be just 0.0 and 1.0.
First, try adding more bins like this (here numBins is 10):
val metrics = new BinaryClassificationMetrics(probabilitiesAndLabels,10);
If you still only have two thresholds of 0 and 1, then check to make sure the way you have defined your predictionAndLabels. You many be having this problem if you have accidentally provided (label, prediction) instead of (prediction, label).

Resources