cross_entropy
std.loss.cross_entropy · Level L1Cross-entropy between a target distribution and the softmax of logits. Calls log_softmax.
−Σᵢ tᵢ·log softmax(z)ᵢ
Signature
cross_entropy(logits: f64[n], target: f64[n]) → f64[]
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.
- input
- operation
- constant
- call
- output
Verification
- Signature proven by NOVA’s shape solver, for every size.
- Agrees with the reference
-np.sum(target * log_softmax(logits))to 80 digits (100-digit arithmetic), on all 40 test cases. - All 40 float64 results inside the running error bound; the closest uses 20% of it.
- Interpreter and NumPy backend return bit-identical results.
- At float32 too: the 40 test cases rounded to float32, and 40 of them inside the running error bound at u = 2⁻²⁴; the closest uses 19% of it.
Accuracy in detail
- correctly rounded (the float64 nearest the exact value)
- 65%
- largest error, in units in the last place
- 2.18
Identity
sha256:33cf1fc43bfd545a043eea67d29a3f1c8bf0fc1251fe9171c47f73e53c80a2b1The semantic hash of the graph. It changes when the program changes, and never when only its documentation does.
Control handle
- Symbol
- Ω:std.loss.cross_entropy · Ω:cross_entropy
- Pins
sha256:04d7fcf938951750466c3749cac4da0edefdaca5c9704f0a5561b17211db6a86this graph and the 2 it reaches through calls- Evidence
sha256:86249ce151706769175ed9c9daa06812958bb5ea04cbb189bff1469abc2d51cdthe hash of its verification record- Needs
- no capability: a pure function
Through NOVA’s control layer, the symbol launches this function only while the program still matches what it pins: a change to this graph, or to any graph it reaches, needs a migration first.