Question

Understanding stochastic gradient descent and derived methods

score 115 · Answer 1 · 2020-01-31 13:14:00

115

Views

Understanding stochastic gradient descent and derived methods

Published on 31 Jan 2020 - 13:14

score 31 · Answer 2 · 2020-02-05 12:28:16

31

Views

If $p^T \nabla f(x) < 0 $ then there exists an $\alpha \ge 0 $ such that $f(x + \alpha p) < f(x)$?

Published on 05 Feb 2020 - 12:28

score 141 · Answer 3 · 2026-03-28 05:28:55

141

Views

Gradient Descent (Geometric) - Why find ascent/descent in first iteration

Published on 28 Mar 2026 - 5:28

score 41 · Answer 4 · 2020-02-10 12:57:49

41

Views

What is the complexity of Gradient descent given sparsity $s$, condition number $k$ and size of the matrix $N$?

Published on 10 Feb 2020 - 12:57

score 658 · Answer 5 · 2020-02-11 03:59:37

658

Views

How to determine if a (cost) function is convex?

Published on 11 Feb 2020 - 3:59

score 38 · Answer 6 · 2020-02-12 06:44:32

38

Views

Poor man's sphere packing in 3D

Published on 12 Feb 2020 - 6:44

score 35 · Answer 7 · 2026-03-25 21:53:30

35

Views

Given two functions' gradients, which one gives more decrease?

Published on 25 Mar 2026 - 21:53

score 97 · Answer 8 · 2026-03-27 05:37:59

97

Views

I need advice on the use of Gradient descent vs. Newton's method to minimise a multi-variable objective function.

Published on 27 Mar 2026 - 5:37

score 293 · Answer 9 · 2020-02-21 02:31:05

293

Views

how does one perform quadratic norm steepest descent

Published on 21 Feb 2020 - 2:31

score 258 · Answer 10 · 2020-02-21 21:56:35

258

Views

Taylor series expansion approximation

Published on 21 Feb 2020 - 21:56

score 168 · Answer 11 · 2020-02-22 04:18:00

168

Views

Does gradient descent really take you down the steepest path?

Published on 22 Feb 2020 - 4:18

score 350 · Answer 12 · 2020-02-25 04:21:38

350

Views

Gradient Descent convergence - multivariate regression

Published on 25 Feb 2020 - 4:21

score 532 · Answer 13 · 2026-03-26 23:59:51

532

Views

Gradient Descent convergence proof - understanding one step with Lipschitz function

Published on 26 Mar 2026 - 23:59

score 165 · Answer 14 · 2020-02-27 10:23:27

165

Views

Minimum Maximum of a function of more than two variables

Published on 27 Feb 2020 - 10:23

score 115 · Answer 15 · 2026-03-28 05:22:01

115

Views

On modifying the gradient in gradient descent when the objective function is not convex nor does it have Lipschitz gradient.

Published on 28 Mar 2026 - 5:22

List Question

Understanding stochastic gradient descent and derived methods

If $p^T \nabla f(x) < 0 $ then there exists an $\alpha \ge 0 $ such that $f(x + \alpha p) < f(x)$?

Gradient Descent (Geometric) - Why find ascent/descent in first iteration

What is the complexity of Gradient descent given sparsity $s$, condition number $k$ and size of the matrix $N$?

How to determine if a (cost) function is convex?

Poor man's sphere packing in 3D

Given two functions' gradients, which one gives more decrease?

I need advice on the use of Gradient descent vs. Newton's method to minimise a multi-variable objective function.

how does one perform quadratic norm steepest descent

Taylor series expansion approximation

Does gradient descent really take you down the steepest path?

Gradient Descent convergence - multivariate regression

Gradient Descent convergence proof - understanding one step with Lipschitz function

Minimum Maximum of a function of more than two variables

On modifying the gradient in gradient descent when the objective function is not convex nor does it have Lipschitz gradient.

Trending Questions

Popular # Hahtags

Popular Questions