This forum is inactive. Browsing/searching possible.
Connect your moderator Slack workspace to receive post notifications:
Computational cost for projected gradient descent
Lectures
·
126
·
2
·
13 Jan '21
What is the Computational cost for projected gradient descent?
Computaional cost for grid search
Lectures
·
82
·
2
·
11 Jan '21
I am having trouble computing the computational cost for grid search. Can someone please help with …
Computational cost
Lectures
·
168
·
4
·
9 Jan '21
If the cost to compute \( \mathbf{e}\) is
$$
O(N*D) + O(N)
$$
and the cost to compute \(…
minibatch implementation
Lectures
·
73
·
3
·
8 Jan '21
Good evening,
Looking online I find different ways to implement minibatch GD. Some select B rand…
second order condition
Lectures
·
82
·
2
·
5 Jan '21
Hi,
In lecture 2 page 22 formula (2) I don't understand why the condition is stated as positive …
Convergence : gradient descent 1-param model
Lectures
·
66
·
1
·
28 Dec '20
How would you prove the convergence of the sequence only for gama in (0;2)?
![Captură de ecran 2…
Subgradients
Lectures
·
189
·
4
·
28 Dec '20
According to the definition of subgradient
$$
\mathcal{L}(\mathbf{u}) \geq \mathcal{L}(\mathbf{…
Constrained optimization & feature normalization
Lectures
·
116
·
2
·
26 Sep '20
Thank you so much for answering all my previous questions :)
I have the following questions fr…
SGD and (N<D)
Lectures
·
82
·
3
·
24 Sep '20
We said that (N<D) case is undetermined for linear regression problem.
But if we use SGD we may ev…
GD: gammas that guarantee convergence
Lectures
·
97
·
3
·
24 Sep '20
Can you explain further in detail how to calculate/compute the range of gammas that guarantee conve…
GD on Hyperparameters
Lectures
·
106
·
5
·
24 Sep '20
In the lecture, Martin mentioned that Grid Search is the simplest but not the best optimization alg…