Skip to main content

Evaluation

omnibias is evaluated along four independent axes. A release is only as good as the weakest one, so each has its own gate.

The four axes

1. Correctness

Closed-form derivatives are checked against an independent ground truth — typically autodiff of the same function — and must agree to float64 round-off (≤ 1e-15). This is a correctness check: the closed form and autodiff compute the same mathematical object two different ways.

2. Parity

The same (activation, order) pair must be bit-identical across PyTorch, JAX, and Keras 3. See cross-backend parity.

3. Soundness

Every rigorous enclosure must contain a dense deterministic grid and a random sample of true values. An enclosure that excludes a true value is unsound and blocks release. See the certified register.

4. Performance

Speed and memory versus autodiff baselines, always reported with the precision and hardware tier, and always with matching answers. See benchmarking.

The metrics that matter

AxisMetricTarget
Correctnessmax abs error vs. ground truth≤ 1e-15 (float64)
Paritymax ULP difference across backends0 (float64)
Soundnessfraction of true samples enclosed1.0
Performancespeedup + memory ratio vs. autodiffreported, not cherry-picked
Evaluate the answer before the speed

A speedup only counts if the answer matches. Always pair a performance number with the correctness check that shows the result is identical to the trusted baseline.

See also