What I Wish Someone Had Told Me About Tensor Computation Libraries
I get confused with tensor computation libraries (or computational graph libraries, or symbolic algebra libraries, or whatever they’re marketing themselves as these days). I was first introduced to PyTorch and TensorFlow and, having no other reference, thought they were prototypical examples of tensor computation libraries. Then I learnt about Theano — an older and less popular project, but different from PyTorch and TensorFlow and better in some meaningful ways. This was followed by JAX, which seemed to be basically NumPy with more bells and whistles (although I couldn’t articulate what exactly they were). Then came the announcement by the PyMC developers that Theano would have a new JAX backend.