-
After merging #241 there are still some DMD variants that lack the parameter to control Tikhonov regularization.
For instance:
+ `hankeldmd.py`
+ `hodmd.py`
+ `spdmd.py`
-
when update grid:
torch._C._LinAlgError: torch.linalg.lstsq: (Batch element 1): The least squares solution could not be computed because the input matrix does not have full rank (error code: 4).
…
-
It might be nice to add support for [ImplicitDifferentiation.jl](https://github.com/JuliaDecisionFocusedLearning/ImplicitDifferentiation.jl) or similar to make the reconstructed image differentiable w…
-
Hello,
Would you have a reference/definition of this iterative Tikhonov regularization ?
I mean a mathematical definition, a plublication,...
Your iterative approach works great but I would like to u…
xmttl updated
7 years ago
-
We have been observing inconsistent dynamic range issues with phase reconstructions across different datasets. When I try sweeping the Tikhonov regularization strength, the *same* FOV would also have …
-
Currently the examples are run with `mode='conv'`. This means GaussPy is performing smoothing with a Gaussian kernel which will lead to much different alpha values than when using `mode='python'`, smo…
-
After our discussion in #157. I decided to read up more on the advantages/disadvantages of using other regularization techniques. I found
[CMARS 2012](https://www.researchgate.net/publication/233…
-
Modify DFO-LS to allow different loss functions (not just sum-of-squares), when the analytic form is known, so full model can be built using first derivatives (e.g. currently, have y -> y^2, with firs…
-
Ridge regression is the most general algorithm for regression. It generalises all the regression methods implemented in this library as the problem of finding W such that the error e = (|| y-Wx ||) i…
-
```
Warning: Matrix is close to singular or badly scaled. Results may be inaccurate. RCOND =
2.234954e-25.
```