Questions tagged [gradient-descent]
Gradient Descent is an algorithm for finding the minimum of a function. It iteratively calculates partial derivatives (gradients) of the function and descends in steps proportional to those partial derivatives. One major application of Gradient Descent is fitting a parameterized model to a set of data: the function to be minimized is an error function for the model.
452
questions
0
votes
0
answers
15
views
Mean Square Error not decreasing during gradient descent
I am currently writing a program which is supposed to implement gradient descent to train a prediction model. I am encountering an error whereby my MSE continuously increases, and the network never ...
- 1
0
votes
0
answers
15
views
Minimize MAE loss for a target that is sum of two other targets
Working on a regression modelling task where my dataset have some feature columns, two more columns A, B and a target column T. The goal is to predict T, and minimize MAE, that is ...
1
vote
2
answers
99
views
Gradient Descent: Is the magnitude in Gradient Vectors arbitrary?
I am only just getting familiar with gradient descent through learning logistic regression. I understand the directional component in the gradient vectors is correct information derived from the slope ...
- 11
0
votes
0
answers
10
views
Why does weight decay produce regularisation in Deep Neural Network?
Weight decay penalizes the model to have smaller weights but how does this help in regularisation?
Any intuition on smaller weights => simpler model?
1
vote
0
answers
26
views
Confusion over taking gradients in Variational Autoencoder (VAE)
I am confused as to when to hold certain parameters constant in a VAE. I will explain with a concrete example.
We can write $\operatorname{ELBO}(\phi, \theta) = \mathbb{E}_{q_{\phi}(z)}\left[\log
\...
- 11
0
votes
0
answers
32
views
Gradients of lower layers of a CNN when gradient of an upper layer is 0?
Say we have a convolutional neural network with an input layer, 3 convolutional layers and an output layer.
Say the gradients with respect to the weights and biases of the third convolutional layer ...
- 147
2
votes
1
answer
292
views
Gradients of lower layers of NN when gradient of an upper layer is 0?
Say we have a neural network with an input layer, a hidden layer and an output layer.
Say the gradients with respect to the weights and biases of the output layer are all 0.
Then, by backpropagation ...
- 147
0
votes
0
answers
18
views
How to calculate the gradient magnitude , orientation and threshold the image intensity values = [10 20 5],[10 20 5] kx=[1 -1] ky=[1 ], [-1]
How to calculate the gradient magnitude , orientation and threshold the image intensity values = [10 20 5],[10 20 5] kx=[1 -1] ky=[1 ], [-1]
image intensity values = [10 20 5]
[10 20 ...
0
votes
0
answers
44
views
Backpropagation and Gradient Descent: Questions on math behind it
I watched this video which goes over backpropagation calculus and read the Wikipedia page on it. This is my understanding of the equations for the algorithm. I have questions regarding the equations ...
- 101
1
vote
1
answer
49
views
Why Cost function is differentiable?
I've a very basic question about cost functions. I'm studying gradient descent and there we're using partial differentiation of features "Theta". But isn't the cost function an absolute ...
- 11
0
votes
2
answers
38
views
Does LinearRegression uses Gradient Descent for finding slope and y-intercept of the best fit line?
I know that Gradient Descent is an optimization algorithm used for optimizing the cost of the loss function.
Does Linear Regression model of the sklearn package use ...
0
votes
0
answers
105
views
TensorFlow Gradient Tape - LookupError (Tandem Neural Network project)
I am trying to train a network by using a custom lost function, then computing the gradient of the loss, and updating the trainable variables in the reverse network (named: reverse_loaded).
For ...
0
votes
1
answer
13
views
feature engineering mechanism
why do we need to rescale some feature having large range I know we do it for faster rate of gradient descent ,but still how does rescaling works? and it doesn't break the model
and does rescaling ...
1
vote
1
answer
26
views
Doubt in gradient , vanishing gradient problem in Back propagation
As per my knowledge, in back propagation- loss function or gradient is used to update the weights.
in back propagation, weights became small w.r.t gradients, this leads to vanishing gradient problem.
...
- 57
0
votes
0
answers
9
views
Correlation between hinge loss function, Langrage function and ai
The function $f(w,b) = \frac{1}{2} ||w||^2$ is our objective function while our constraints are all the correct classifications of the data points expressed as $g(w,b) = \sum_{i=1}^{l} (y_i (x_i \cdot ...
- 1
0
votes
1
answer
42
views
Gradients Exploding with Custom Gradient and 2 layer MLP
I am training a 2 layer MLP on an off-policy learning-to-rank task, where the input is a list of documents against a query with a feature vector for each query-document pair, i.e. if there are M ...
- 3,775
0
votes
0
answers
26
views
cost function including constrain on vector norm
I'm playing with collaborative implementation using numpy.
As a reminder, we are given a matrix $R$ of user ratings for movies. Let's assume there are 3 users and 4 movies. The data matrix we are ...
- 1
0
votes
0
answers
30
views
Exploring the Concept of Gradient Flow
Understanding the concept of "Gradient Flow" can be quite difficult as there is a lack of widely recognized and clearly defined resources that provide a comprehensive explanation. Although ...
- 11
1
vote
2
answers
2k
views
What exactly is Gradient norm?
I found that there is no common resource and well defined definition for "Gradient norm", most search results are based on ML experts providing answers which involves gradient norm or papers ...
- 11
0
votes
1
answer
49
views
How exactly does the mini batch method work?
I mean let's say I have a mini batch, I take an example from it and for it I do the following:
I do forward propagation.
Using the output after forward propogation - I calculate the gradients of the ...
- 11
0
votes
1
answer
114
views
Affine layer - gradient shape
In course cs231n, I need to implement backward pass computation for an affine (linear) layer:
...
0
votes
0
answers
16
views
Is It Fair to Simplify Gradient Descent as Derivative of Loss Function * Derivative of Activation Function * Derivative of Neuron?
Recently I've been trying to think of an easier way to wrap my head around gradient descent rather than just manually derive loss function with respect to weights (and chain and yada yada yada). I was ...
- 1
1
vote
2
answers
36
views
Gradient vector starts to increase at some point, gradient descent from scratch
I have a simple linear function y = w0 + w1 * x, where w0 and w1 are weights,
And I'm trying to implement a gradient descent for it. I wrote the function and tested in on the data(a dataset of two ...
- 13
0
votes
0
answers
13
views
My linear regression doesn't work when i try to calculate theta1
I want to create my own linear regression. But my formula of the coefficient theta1 doesn't work i have big values :
...
0
votes
1
answer
16
views
moments of weight vectors in Adam
When performing backpropagation with Adam algorithm, are the moment and the second moment of the weight vectors calculated also for the weights in hidden layers?
- 152
0
votes
1
answer
29
views
what is static objective function
Paper on Adam mentions Stationary Objective function. I am not able to find its definition on Internet (or may be it's there with some other name and I am not able to figure it out). I will be ...
- 203
0
votes
1
answer
25
views
AdaGrad denominator exponents comparison
Adagrad adapts the learning rate $ \alpha $ all along the gradient descent process, by dividing each weight on a quantity based on the sum of the previous squared gradient up to time $ t $. Therefore, ...
1
vote
0
answers
23
views
How to calculate gradient of MSE in backpropagation? [duplicate]
I want to implement a neural network from scratch to solve linear regression by using backpropagation. I don't understand how to compute the gradient of the MSE cost function with respect to each ...
- 152
0
votes
0
answers
19
views
Batchnorm and gradient attenuation
Am I understood right that if we put batchnorm layer after every conv layer and our network is very deep, then we won't have a problem of gradient attenuation? In other words, is it true that ...
- 101
0
votes
0
answers
26
views
Understanding gradient of skip gram
I am trying to understand gradient calculation for skip gram with softmax output and cross entropy loss.
I am referring these articles: 1, 2, 3.
The all calculate the error as follows:
$$E=-\sum_{c=1}...
- 103
0
votes
0
answers
20
views
Polynomial Regression coefficient extraction after data normalisation for Mini-Batch SGD
I've written python function that uses a stochastic mini-batch algorithm to compute the optimal polynomial coefficients for a given degree $m$, however this involved normalising the data where
$$
x' = ...
- 101
0
votes
1
answer
230
views
Why is cross entropy loss averaged and not used directly as a sum during model training(such as in neural networks)
Why is the cross entropy loss for all training examples(or the training examples in a batch) averaged over size of the training set(or batch size) ?
Why is it not just summed and used ?
1
vote
1
answer
32
views
How train a pre-trained model based on new dataset?
I have trained a deep nn model based on some existing data. In the meantime, I have collected more data and label them so that I can feed it to the model to improve its performance. The questions is, ...
- 263
0
votes
0
answers
18
views
How to derive expression for gradient in BPPT
I have the following problem: I am trying to derive final expressions for error gradients in a simple recurrent neural network (Backpropagation through Time, BPPT). The parameters and state update ...
0
votes
1
answer
95
views
GAN Generator Backpropagation Gradient Shape Doesn't Match
In the TensorFlow example (https://www.tensorflow.org/tutorials/generative/dcgan#the_discriminator) the discriminator has a single output neuron (assume batch_size=1).
Then over in the training loop ...
- 3
0
votes
0
answers
189
views
Understanding the stochastic average gradient (SAG) algorithm used in sklearn
For pedagogical purposes I've been trying to create my own implementation of the stochastic average gradient (SAG) algorithm in a logistic regression framework. Page 10 of the associated paper ...
0
votes
0
answers
19
views
What is the meaning of uncentered variance?
I read some articles that describe ADAM optimizer and they used uncentered variance expression.
I'm not sure I understand the ...
- 363
0
votes
1
answer
77
views
What does the ellipse in Gradient descent describes?
I saw multiple articles describes GD or SGD with the following diagram:
I didn't saw any explanation about the ellipses.
What ...
- 363
0
votes
0
answers
10
views
In RMSProp how squares of the gradients dumps out the oscillations?
I read multiple articles that say that RMSProp use the squares of the gradients in order to dump oscillations.
It's not intuitive to me how the squares of the ...
- 363
1
vote
0
answers
194
views
How Adam optimizer influence the learning rate? [closed]
I read some papers about how ADAM optimizer works, and there are some issues which seems that are confusing:
ADAM equations are:
...
- 363
0
votes
1
answer
55
views
What will happen if we apply Gradient Ascent?
I have built a simple neural network on MNIST, but instead of moving toward the opposite direction of gradients, I moved in the same direction of it just by applying( pytorch ):
...
- 263
1
vote
1
answer
490
views
Does settings $\beta_1 = 0$ or $\beta_2 = 0$ means that ADAM behaves as RMSprop or Momentum?
I read on ADAM optimizer, and I saw multiple quotes which say that ADAM is a combination of Momentum and RMSprop optimizers.
So if we:
Set $\beta_1 = 0$ does it means that ADAM behaves exactly as ...
- 363
0
votes
1
answer
59
views
Normalising data for simple linear regression
Consider a simple linear regression problem where:
X = [1,2,3,4,5,100,200]
Y= [2,4,6,8,10,200,400]
Clearly, the relationship is of the form $y=2x$; While trying ...
- 13
0
votes
0
answers
19
views
How backward() is calculated in CrossEntropyLoss?
I have a simple Linear model and I need to calculate the loss for it. I applied two CrossEntropyLoss and NLLLoss but I want to ...
- 263
6
votes
4
answers
1k
views
How to fit a math formula to data?
I have math formula and some data and I need to fit the data to this model.
The math is like. $y(x) = ax^k + b$ and I need to estimate the $a$ and the $b$.
I have triet gradient descend to estimate ...
- 263
0
votes
1
answer
371
views
Why does Adam outperform SGD in logistic regression?
I am training a logistic regression model. In case it matters, the features are 1376-dimensional embeddings output from a neural network. I tried both SGD and Adam with a learning rate of $10^{-3}$ ...
- 113
0
votes
1
answer
268
views
Difference between sklearn's LogisticRegression and SGDClassifier?
What is the difference between sklearn's LogisticRegression classifier and its SGDClassifier? I understand that the SGD is an ...
0
votes
0
answers
62
views
Why backpropagation is done in every epoch when loss is always scalar?
I understand the backpropagation algorithm that it calculates the derivate of loss with respect to all the parameters in the neural network. My question is this derivate is constant right because the ...
- 101
0
votes
0
answers
46
views
Question about input value in Gradient descent
I am currently going through Udacity´s online course "Intro to Deep Learning with PyTorch". In one of the videos covering the Gradient descent algorithm they show the formula for how the ...
- 1
0
votes
1
answer
183
views
Setting shape of RaggedTensor with Known Shape
I'm working with RaggedTensors to manipulate a dense tensor. Something like this :
...
- 53