Mo Tiwari

Often with the function `net.summary.add_scalar_value(...)`, I intermittently get the following error: ` requests.exceptions.ConnectionError: HTTPConnectionPool(host=IP, port=8889): Max retries exceeded with url: /data/scalars?xp=VGG&name=Train%20R%5E2 (Caused by NewConnectionError(': Failed to establish a new connection:...

Several bugs with 'Using GraphWave' iPython notebook

1

Thanks for putting together the tutorial in the iPython notebook! While trying to use it, I came across the following bugs and suggested fixes: 1. `from graphwave.shapes import build_graph` should...

I think this would really help make it easier to use! The package could use a `setup.py` :)

[Right now](https://pypi.org/project/banditpam/3.0.4/#files), wheels only exist for `manylinux` and `musllinux` `i686` and `x86_64` architectures. We should compile the wheels for these architectures as well so that end-users don't have to build...

Opening this PR to compare code and test Github actions Fixes #167

Consider sampling *without* replacement

1

That way we wouldn't have to recompute the change in loss for all reference points for `compute_exactly`

WIP. Do not review. Creating this review only to easily understand why swap chaining is happening in the `slowdown` branch and where the divergence in behavior from `main` comes from.

Support arbitrary distance metrics

2

We should have an easy way for users to incorporate their own dissimilarity metrics. Users should be able to write their dissimilarity metric in Python, which is then called via...