l2_penalty
std.loss.l2_penalty · Level L0L2 weight penalty. Calls frobenius_sq.
λ·‖W‖²_F
Signature
l2_penalty(W: f64[k, n], lam: f64[]) → 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.
- Equal to the reference
lam * np.sum(W ** 2)in exact rational arithmetic, on all 40 test cases. - All 40 float64 results inside the running error bound; the closest uses 72% 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 51% of it.
Accuracy in detail
- correctly rounded (the float64 nearest the exact value)
- 63%
- largest error, in units in the last place
- 1.43
Identity
sha256:04bbd2b304fc1dbdcb07503b57b9a9bf1b8788e5113b2ff9e45f3a6c0a5d2f38The semantic hash of the graph. It changes when the program changes, and never when only its documentation does.
Control handle
- Symbol
- Ω:std.loss.l2_penalty · Ω:l2_penalty
- Pins
sha256:60291efc994ec30a754fa15e4130a08c0b448030fc32066d7a1a433aa7ed13ffthis graph and the 1 it reaches through calls- Evidence
sha256:d47903d1a565e7e41c12aa60f5120c0ef1ecb7d071bdc99bb326d65005e027c5the 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.