StackOverflow Questions for Tag: automatic-differentiation

Zoe Zhao
Zoe Zhao

Reputation: 11

Why do custom backward functions and torch.autograd yield different results after network training?

Score: 1

Views: 31

Answers: 1

Read More
Jimut123
Jimut123

Reputation: 518

Any faster and memory-efficient alternative of torch.autograd.functional.jacobian(model.decoder, latent_l)?

Score: 0

Views: 54

Answers: 1

Read More
Peter234
Peter234

Reputation: 1052

How to use torch.unique to filter duplicate values, calculate an expensive function, map it back, and then calculate the gradient?

Score: 0

Views: 74

Answers: 1

Read More
Moody
Moody

Reputation: 1417

Difference between symbolic differentiation and automatic differentiation?

Score: 43

Views: 18674

Answers: 4

Read More
Julier
Julier

Reputation: 25

The analogue of torch.autograd in TensorFlow

Score: 0

Views: 118

Answers: 1

Read More
Andreas Schuldei
Andreas Schuldei

Reputation: 405

How to Properly Track Gradients with MyGrad When Using Scipy's RectBivariateSpline for Interpolation?

Score: 1

Views: 71

Answers: 1

Read More
James Yong
James Yong

Reputation: 31

How to handle errors caused by non-JAX objects (such as scipy.sparse.csr_matrix) in JAX custom_vjp?

Score: 1

Views: 79

Answers: 1

Read More
Nick Alger
Nick Alger

Reputation: 1104

Forward-over-reverse mode Hessian-vector product in Jax: how smart is jax.jvp at re-using computations?

Score: 1

Views: 86

Answers: 0

Read More
Samuel Beaussant
Samuel Beaussant

Reputation: 3

Discrepancy in BatchNorm2d Gradient Calculation Between TensorFlow and PyTorch

Score: 0

Views: 47

Answers: 1

Read More
HaineBaie
HaineBaie

Reputation: 1

How to compute Higher-Order Gradients Across Two Networks in PyTorch? (ML, Autograd)

Score: 0

Views: 37

Answers: 0

Read More
Shawn
Shawn

Reputation: 89

Taking derivatives with multiple inputs in JAX

Score: 1

Views: 115

Answers: 1

Read More
Nsss123
Nsss123

Reputation: 11

Error in automatic derivative calculation with pytorch

Score: 1

Views: 56

Answers: 1

Read More
Jingyang Wang
Jingyang Wang

Reputation: 323

JAX custom_jvp with 'None' output leads to TypeError

Score: 1

Views: 70

Answers: 1

Read More
liang alex
liang alex

Reputation: 1

In PyTorch, when using loss.backward() to compute gradients, how can I prevent it from overriding the gradients I've manually computed?

Score: 0

Views: 34

Answers: 0

Read More
R S
R S

Reputation: 11

Derivative of Gaussian Blur with respect to the pixels

Score: 1

Views: 130

Answers: 0

Read More
Enigmatisms
Enigmatisms

Reputation: 175

Whether there is any need to modify the backward function in pytorch?

Score: 0

Views: 147

Answers: 1

Read More
0xbadf00d
0xbadf00d

Reputation: 18218

Computing the Jacobian of an image: How to reshape the numpy array properly?

Score: 2

Views: 174

Answers: 1

Read More
fmg
fmg

Reputation: 925

Update step in PyTorch implementation of Newton's method

Score: 3

Views: 3563

Answers: 2

Read More
0xbadf00d
0xbadf00d

Reputation: 18218

How to generate jacobian of a tensor-valued function using torch.autograd?

Score: 0

Views: 138

Answers: 1

Read More
klpskp
klpskp

Reputation: 61

Calculating two gradients in pytorch and reusing an intermediate gradient

Score: 4

Views: 201

Answers: 2

Read More
PreviousPage 1Next