Skip to main content

Benchmark results

All numbers below are float64 with answers identical to autodiff to ≤ 1e-15. Read the methodology first — the rules there are what make these meaningful.

Headline: the Laplacian at scale

At input dimension D = 240, against a dense-Hessian autodiff baseline:

Metricomnibias vs. dense-Hessian autodiff
Speed68× – 199× faster
Memory63× – 108× less
Answeridentical to ≤ 1e-15

The spread reflects the hidden-width / batch regime; see methodology for the sweep configuration.

Scaling shape: O(1) in D

The Laplacian's D-dependent term (‖W·…‖²-type contraction) is computed once and reused, so the per-sample overhead stays roughly flat as D grows.

Iterated Laplacian: flat in k

Orderomnibiasnested forward-Laplacian
Δ (k=1)~0.1 msbaseline
Δ² (k=2)~0.1 msslower
Δ³ (k=3)~0.1 ms~480× slower
Δ⁴ (k=4)~0.1 msout of memory

This is the qualitative win: closed form is flat in order, nested autodiff is not.

VMC local kinetic energy

On a Beryllium 8-determinant body, the omnibias local kinetic energy is bit-identical (rel-err 0.0, ULP) to FermiNet's default autograd Laplacian, and ≤ 5.07e-15 versus folx — a drop-in with no change to the energy curve.

Reproduce the trend in seconds

You will not reproduce the absolute full-tier numbers on a laptop, but the CPU smoke tier reproduces the shape (flat-in-D, flat-in-k) in seconds. See the performance guide.

See also