embedding_lookup

std.nn.embedding_lookup · Level L3

Embedding lookup: the rows of the table E at the integer ids, in order (repeats allowed).

Yᵢ = E[idsᵢ]

Signature

embedding_lookup(E: f64[v, d], ids: i64[k]) → f64[k, d]

Structure

The function as NOVA stores it: one box per input, operation and output, and arrows that carry values. A double border marks another library function this one runs — called once, or by Scan once per element; select it to open that function.

Ef64[v, d]idsi64[k]GatherYYf64[k, d]
  • input
  • operation
  • constant
  • call
  • output

Verification

  • Signature proven by NOVA’s shape solver, for every size.
  • Equal to the reference np.take(E, ids, axis=0) in exact rational arithmetic, on all 40 test cases.
  • All 598 float64 results are exact: the error is zero.
  • Interpreter and NumPy backend return bit-identical results.
Accuracy in detail
correctly rounded (the float64 nearest the exact value)
100%
bit-equal to the NumPy formula in float64
100%
largest error, in units in the last place
0

Identity

Calls
—
Called by
embedding_bag_mean
sha256:368b6e6fa17aa116e98faacc219cd8b85757f1295e48055aa42f211a6b14dbb4

The semantic hash of the graph. It changes when the program changes, and never when only its documentation does.