Question

Confusion after attempting to apply chain rule with respect to matrix, using a Frobenius product.

score 146 · Answer 1 · 2018-05-20 11:58:15

146

Views

Confusion after attempting to apply chain rule with respect to matrix, using a Frobenius product.

Published on 20 May 2018 - 11:58

score 52 · Answer 2 · 2026-03-25 01:27:14

52

Views

Need help in understanding a section of a paper.

Published on 25 Mar 2026 - 1:27

score 164 · Answer 3 · 2018-05-23 23:33:33

164

Views

Minimizing $f(\vec{x})$ along a line via the line search algorithm

Published on 23 May 2018 - 23:33

score 149 · Answer 4 · 2018-05-25 04:36:53

149

Views

How to find the minimum of a noisy function that has very narrow valleys?

Published on 25 May 2018 - 4:36

score 405 · Answer 5 · 2018-05-26 19:45:53

405

Views

Can the directional derivative be considered a total derivative?

Published on 26 May 2018 - 19:45

score 272 · Answer 6 · 2026-03-24 23:45:53

272

Views

How to compute gradient of a custom loss function in neural networks and make sure it is diffentiable?

Published on 24 Mar 2026 - 23:45

score 385 · Answer 7 · 2026-03-22 12:17:52

385

Views

Multiplicative update rules for NMF

Published on 22 Mar 2026 - 12:17

score 68 · Answer 8 · 2026-03-24 23:41:03

68

Views

Quadratic function optimum not aligning with implementation.

Published on 24 Mar 2026 - 23:41

score 57 · Answer 9 · 2018-06-06 02:51:07

57

Views

Counterexample: is there a solution of $\dot{x}(t)=-\nabla f(x)(t)$ with infinite length?

Published on 06 Jun 2018 - 2:51

score 50 · Answer 10 · 2026-03-24 22:06:52

50

Views

Understanding a question about gradient descent flow

Published on 24 Mar 2026 - 22:06

score 215 · Answer 11 · 2026-03-22 03:42:01

215

Views

Convergence of non-convex optimization algorithms to an $\epsilon$-accurate solution

Published on 22 Mar 2026 - 3:42

score 388 · Answer 12 · 2026-03-25 04:43:24

388

Views

How are both of these true: $J = \nabla f ^T $, and also $\nabla f = J^T f$?

Published on 25 Mar 2026 - 4:43

score 474 · Answer 13 · 2026-03-22 01:06:24

474

Views

Gradient descent converges to critical points for non-convex functions

Published on 22 Mar 2026 - 1:06

score 441 · Answer 14 · 2018-06-11 16:57:04

441

Views

What is difference between "Frank–Wolfe algorithm" and "Gradient steepest descent algorithm"?

Published on 11 Jun 2018 - 16:57

score 258 · Answer 15 · 2026-03-25 03:00:27

258

Views

Why not: Multiple Steps in the Direction of One Gradient

Published on 25 Mar 2026 - 3:00

List Question

Confusion after attempting to apply chain rule with respect to matrix, using a Frobenius product.

Need help in understanding a section of a paper.

Minimizing $f(\vec{x})$ along a line via the line search algorithm

How to find the minimum of a noisy function that has very narrow valleys?

Can the directional derivative be considered a total derivative?

How to compute gradient of a custom loss function in neural networks and make sure it is diffentiable?

Multiplicative update rules for NMF

Quadratic function optimum not aligning with implementation.

Counterexample: is there a solution of $\dot{x}(t)=-\nabla f(x)(t)$ with infinite length?

Understanding a question about gradient descent flow

Convergence of non-convex optimization algorithms to an $\epsilon$-accurate solution

How are both of these true: $J = \nabla f ^T $, and also $\nabla f = J^T f$?

Gradient descent converges to critical points for non-convex functions

What is difference between "Frank–Wolfe algorithm" and "Gradient steepest descent algorithm"?

Why not: Multiple Steps in the Direction of One Gradient

Trending Questions

Popular # Hahtags

Popular Questions