You highlight that AlphaTensor can be used to optimize for a variety of distance metrics (speed, memory, numerical stability, energy usage, etc.). Would the distance metrics be what changed if you were using AlphaTensor to find better matrix multiplication algorithms for sparse matrices? What would this distance metric look like, if so
Hi, I mentioned "distinct" metrics. Just like the ones you mention. In order to apply AlphaTensor to sparse matrices, one would only need to change the dataset of randomly generated synthetic data (to contain only examples of sparse matrices). Then one could optimize for any metric of choice.
