On: Einsum Is All You Need – Einstein Summation in Dee...

[mhh__]

Absolutely yes.

Doing tensor magic without einstein notation will make you shoot yourself, and even you don't someone else will if publish it.

The only real problem I have with it personally is the abstraction of upper and lower indices, which I constantly forget the conventions as to which is which.

[krastanov → mhh__]

This is interesting... I love the notation, but mainly because how upper and lower indices make it easy to distinguish vectors and forms (not that it matters in ML where everything is "euclidean").

[joppy → krastanov]

Upper and lower indices are great, but are still unrelated to the convention of dropping the big sigma at the front.

[antidesitter → krastanov]

> not that it matters in ML where everything is "euclidean"

Non-euclidean spaces are actually quite common in ML, but many people don’t realize the spaces they’re working in are non-euclidean!

[improbable22 → antidesitter]

Would be curious to hear what you have in mind here -- could you expand?

[g82918 → mhh__]

Co -> low, primes below.