We lifted 12 functions out of this paper's own repositories and ran 10 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| dyballa/ian | canonical | 10 of 12 |
| Function | Status | Where it lives |
|---|---|---|
| computeIsomap | Ran | dyballa/ian/ian/embed_utils.py code served (permissive licence) · get_code("2fefda71cf8661c2") |
| computeMutualAdjacencyMatrix | Ran | dyballa/ian/ian/ian.py code served (permissive licence) · get_code("fdd9af6c57e502fa") |
| computeSparseGabriel | Ran | dyballa/ian/ian/ian.py code served (permissive licence) · get_code("2ed344a806ffec7d") |
| diffusionMapFromK | Ran | dyballa/ian/ian/embed_utils.py code served (permissive licence) · get_code("9dd9fa49ae6ab154") |
| diffusionMapSparseK | Ran | dyballa/ian/ian/embed_utils.py code served (permissive licence) · get_code("480036e972bbd8fa") |
| getSparseMultiScaleK | Ran | dyballa/ian/ian/ian.py code served (permissive licence) · get_code("a2a0c1d30c270b38") |
| getTri | Ran | dyballa/ian/ian/utils.py code served (permissive licence) · get_code("259b6299bd7c2660") |
| my_kendalltau | Ran | dyballa/ian/ian/utils.py code served (permissive licence) · get_code("0e91f8ea9b4b0e63") |
| plot2dScatter | Ran | dyballa/ian/ian/dset_utils.py code served (permissive licence) · get_code("43c5a5c9ee40c0e6") |
| subps | Ran | dyballa/ian/ian/utils.py code served (permissive licence) · get_code("a7d98dad875de668") |
| clipped_cmap | Not yet run | dyballa/ian/ian/dset_utils.py code served (permissive licence) · get_code("d433545bf967db52") |
| plot3dScatter | Not yet run | dyballa/ian/ian/dset_utils.py code served (permissive licence) · get_code("e8225a7b1da1cfbe") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Invoking the manifold assumption in machine learning requires knowledge of the manifold's geometry and dimension, and theory dictates how many samples are required. However, in applications data are limited, sampling may not be uniform, and manifold properties are unknown and (possibly) non-pure; this implies that neighborhoods must adapt to the local structure. We introduce an algorithm for inferring adaptive neighborhoods for data given by a similarity kernel. Starting with a locally-conservative neighborhood (Gabriel) graph, we sparsify it iteratively according to a weighted counterpart. In each step, a linear program yields minimal neighborhoods globally and a volumetric statistic reveals neighbor outliers likely to violate manifold geometry. We apply our adaptive neighborhoods to non-linear dimensionality reduction, geodesic computation and dimension estimation. A comparison against standard algorithms using, e.g., k-nearest neighbors, demonstrates their usefulness. Code for our algorithm will be available at https://github.com/dyballa/IAN
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2208.09123")
get_code_for_paper("2208.09123")
have("2208.09123")
Connect an agent — have() is free.