Question

Is there a nice matrix expression for the gradient of the cross-entropy for multinomial logistic regression?

score 102 · Answer 1 · 2026-03-24 15:37:31

102

Views

Is there a nice matrix expression for the gradient of the cross-entropy for multinomial logistic regression?

Published on 24 Mar 2026 - 15:37

score 1.4k · Answer 2 · 2018-04-19 00:09:05

1.4k

Views

Solving a linear program with (sub) gradient descent

Published on 19 Apr 2018 - 0:09

score 636 · Answer 3 · 2018-04-21 18:56:47

636

Views

Selecting the Step-length in Coordinate Descent?

Published on 21 Apr 2018 - 18:56

score 126 · Answer 4 · 2018-04-26 13:51:11

126

Views

Gradient descent - contour map

Published on 26 Apr 2018 - 13:51

score 471 · Answer 5 · 2026-03-16 15:13:01

471

Views

For what class of functions is steepest descent guaranteed to converge in finite number of iterations?

Published on 16 Mar 2026 - 15:13

score 64 · Answer 6 · 2018-04-28 18:52:26

64

Views

choosing optimal scalar in gradient descent algorithm

Published on 28 Apr 2018 - 18:52

score 154 · Answer 7 · 2018-04-29 06:53:14

154

Views

Is this Gradient Descent method or something else?

Published on 29 Apr 2018 - 6:53

score 143 · Answer 8 · 2018-04-29 08:17:20

143

Views

Is the greatest descent direction exactly - the greatest ascent direction?

Published on 29 Apr 2018 - 8:17

score 269 · Answer 9 · 2026-03-22 15:11:31

269

Views

How to prove that Leven Marquardt always results in a descent direction (Proof verification)?

Published on 22 Mar 2026 - 15:11

score 1k · Answer 10 · 2026-03-21 21:59:52

1k

Views

Convergence to local minimum of gradient descent with exact line search for $C^1$ function

Published on 21 Mar 2026 - 21:59

score 239 · Answer 11 · 2026-03-21 21:20:21

239

Views

How to run gradient descent algorithm when parameter space is constrained?

Published on 21 Mar 2026 - 21:20

score 138 · Answer 12 · 2018-05-16 23:07:34

138

Views

Prove existance of positive step size for descent direction

Published on 16 May 2018 - 23:07

score 327 · Answer 13 · 2026-03-22 13:37:57

327

Views

Convergence rate (to a local minimum) of gradient descent for a $C^3$ function

Published on 22 Mar 2026 - 13:37

score 1.2k · Answer 14 · 2026-03-25 05:05:27

1.2k

Views

Coordinate Lipschitz constant vs standard Lipschitz constant

Published on 25 Mar 2026 - 5:05

score 2k · Answer 15 · 2018-05-20 11:23:09

2k

Views

Why transpose in gradient descent?

Published on 20 May 2018 - 11:23

List Question

Is there a nice matrix expression for the gradient of the cross-entropy for multinomial logistic regression?

Solving a linear program with (sub) gradient descent

Selecting the Step-length in Coordinate Descent?

Gradient descent - contour map

For what class of functions is steepest descent guaranteed to converge in finite number of iterations?

choosing optimal scalar in gradient descent algorithm

Is this Gradient Descent method or something else?

Is the greatest descent direction exactly - the greatest ascent direction?

How to prove that Leven Marquardt always results in a descent direction (Proof verification)?

Convergence to local minimum of gradient descent with exact line search for $C^1$ function

How to run gradient descent algorithm when parameter space is constrained?

Prove existance of positive step size for descent direction

Convergence rate (to a local minimum) of gradient descent for a $C^3$ function

Coordinate Lipschitz constant vs standard Lipschitz constant

Why transpose in gradient descent?

Trending Questions

Popular # Hahtags

Popular Questions