-
**Describe the bug**
The `min_grad_norm` parameter is unused in `Barnes_Hut` tSNE:
https://github.com/rapidsai/cuml/blob/640baaee711bdb9d623de768189776dedfd700b6/cpp/src/tsne/barnes_hut.cuh#L44-L5…
-
Does the TSNE algorithm implemented in cmml has a maximal perplexity? I used the following code to create a TSNE object, the perplexity parameter seems to have no impact on the result.
from cuml.m…
-
#### Describe the bug
While working on https://github.com/conda-forge/scikit-learn-feedstock/pull/123, I found that `manifold/tests/test_t_sne.py::test_uniform_grid[barnes_hut]` fails on ppc64l…
-
I notice both cugraph and cuml are using a set of barnes-hut kernels that appear to have originated from the same place. It would be nice to centralize these implementations in RAFT so that we can sha…
-
```
________________________ test_uniform_grid[barnes_hut] _________________________
method = 'barnes_hut'
@pytest.mark.parametrize('method', ['barnes_hut', 'exact'])
def test_uniform_…
-
I experienced a hard Python crash on some real-life data. It turns out it's a call to `.minimum_spanning_tree_.plot()` when many points are exactly equal. A minimal example to reproduce:
```
import …
-
**Describe the solution you'd like**
Currently, if a user wants to use a custom distance metric for TSNE or UMAP, they need to _both_ input the original features (X), as well as the distance matrix (…
-
## Feature
When compiling programs such as scikit-learn which leverage numpy, quite often you will find them including the numpy include paths by using something similar to:
```
config.add…
-
https://github.com/Lv-291/wasm-bhtsne
-
Using `method=tDistributedStochasticNeighborEmbedding` in combination with `withDistance()` is not supported.
Laurens van der Maaten says for using a custom metric, the Vantage-Point Tree needs to …
ypnos updated
6 years ago