|
About the autograd category
|
|
0
|
4013
|
May 13, 2017
|
|
How to make a manually changed loss work in backpropagation
|
|
1
|
14
|
December 3, 2025
|
|
torch.autograd.Function and free function
|
|
2
|
33
|
December 3, 2025
|
|
Autograd and dead-code elimination
|
|
2
|
64
|
November 18, 2025
|
|
Does PyTorch muon optimizer supports 4D weights?
|
|
1
|
30
|
November 17, 2025
|
|
Gradient ascent on some parameters while descent on others in a single model
|
|
3
|
52
|
November 11, 2025
|
|
Batchnorm and back-propagation
|
|
8
|
4014
|
November 3, 2025
|
|
How to debug origin of nans in gradient of custom module
|
|
3
|
43
|
October 29, 2025
|
|
Optimizing a mask instead of weights
|
|
2
|
48
|
October 27, 2025
|
|
PyTorch AD with non-python functions
|
|
1
|
30
|
October 22, 2025
|
|
Brenier maps in Pytorch
|
|
1
|
35
|
October 18, 2025
|
|
Updating Selected parameters in each epoch
|
|
1
|
24
|
October 17, 2025
|
|
No grad & Autocast not working together
|
|
1
|
30
|
October 14, 2025
|
|
How to do back propagation with loss = ||f_{\Theta + \Delta P}(X) - Y||^2 + ||\Delta P||^2 instead of the usual loss = || f_{\Theta + \Delta}(X) - Y ||^2?
|
|
2
|
31
|
October 14, 2025
|
|
"RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [64, 1]], which is output 0 of AsStridedBackward0, is at version 3; expected version 2 instead. Hint: the backtrace further a
|
|
10
|
33107
|
October 9, 2025
|
|
Defining loss that maximizes separation
|
|
0
|
30
|
October 1, 2025
|
|
Ablation Hook I created seems to affect the calculations of the gradients on later layers
|
|
5
|
46
|
September 30, 2025
|
|
How do I set the order of pytorch hooks?
|
|
5
|
65
|
September 29, 2025
|
|
Updating tensors that are used in backpropagation but are not network parameters
|
|
2
|
65
|
September 20, 2025
|
|
Making autograd saved tensors hooks specific to certain arguments
|
|
8
|
237
|
September 17, 2025
|
|
what happens when I use torch.profiler.profile with activities=[torch.profiler.ProfilerActivity.CPU, torch.profiler.ProfilerActivity.CUDA]
|
|
1
|
506
|
September 16, 2025
|
|
Autograd engine thread creation
|
|
2
|
51
|
September 8, 2025
|
|
Solving PDEs using neural networks
|
|
1
|
2449
|
September 5, 2025
|
|
Hessian Vector Product for discounted-return-based loss function
|
|
2
|
56
|
September 2, 2025
|
|
How does torch.where work in autograd
|
|
2
|
57
|
September 2, 2025
|
|
Segmentation fault when calling .backward() after moving data to GPU (PyTorch + CUDA 12.1)
|
|
7
|
204
|
August 28, 2025
|
|
RuntimeError: derivative for aten::grid_sampler_3d_backward is not implemented
|
|
3
|
444
|
August 24, 2025
|
|
2nd derivative for attn is not working
|
|
3
|
646
|
August 20, 2025
|
|
Forward autodiff : Multiplying by python float changes the dual dtype in some situations
|
|
4
|
101
|
August 13, 2025
|
|
Skip the calculation of gradients for some layer after forward pass
|
|
1
|
47
|
August 9, 2025
|