Skip to content

Latest commit

 

History

History
60 lines (47 loc) · 3.28 KB

README.md

File metadata and controls

60 lines (47 loc) · 3.28 KB

Feynman benchmarks

Thirteen synthetic regression tasks are registered in Program.cs. Inputs are sampled independently and uniformly in the order shown below. Physical constants are variable inputs; h denotes reduced Planck's constant (ℏ).

Fifteen further AI Feynman equations are registered as a development set (developmentSets in the same file) and are used only for pilots that choose budgets and settings; they are not part of the evaluation.

With --noise s, training and validation targets receive Gaussian noise with standard deviation s times the clean target's (fixed noise seed, drawn per row in row order); the test partition is scored against the clean and the noisy targets. The study uses s = 0.1 for a noisy subset of conditions.

Runner identifier / descriptor Inputs in descriptor order Domains in that order Target expression
I.6.20 / Feynman2 sigma, theta [1,3], [1,3] exp(-theta²/(2 sigma²))/(sqrt(2 pi) sigma)
I.9.18 / Feynman5 m1, m2, G, x1, x2, y1, y2, z1, z2 [1,2]³, [3,4], [1,2], [3,4], [1,2], [3,4], [1,2] G m1 m2 / ((x2-x1)²+(y2-y1)²+(z2-z1)²)
I.15.3.x / Feynman17 x, u, c, t [5,10], [1,2], [3,20], [1,2] (x-u t)/sqrt(1-u²/c²)
I.30.5 / Feynman31 lambd, d, n [1,2], [2,5], [1,5] asin(lambd/(n d))
I.32.17 / Feynman33 epsilon, c, Ef, r, omega, omega_0 [1,2]⁵, [3,5] (epsilon c Ef²/2)(8 pi r²/3) omega⁴/(omega²-omega_0²)²
I.41.16 / Feynman44 omega, T, h, kb, c [1,5]⁵ h omega³/(pi² c² (exp(h omega/(kb T))-1))
I.48.20 / Feynman50 m, v, c [1,5], [1,2], [3,20] m c²/sqrt(1-v²/c²)
II.6.15a / Feynman56 epsilon, p_d, r, x, y, z [1,3]⁶ 3 p_d z sqrt(x²+y²)/(4 pi epsilon r⁵)
II.11.27 / Feynman64 n, alpha, epsilon, Ef [0,1]², [1,2]² n alpha epsilon Ef/(1-n alpha/3)
II.11.28 / Feynman65 n, alpha [0,1]² 1+n alpha/(1-n alpha/3)
II.35.21 / Feynman81 n_rho, mom, B, kb, T [1,5]⁵ n_rho mom tanh(mom B/(kb T))
III.9.52 / Feynman90 p_d, Ef, t, h, omega, omega_0 [1,3]⁴, [1,5]² p_d Ef t/h sinc²((omega-omega_0)t/2)
III.10.19 / Feynman91 mom, Bx, By, Bz [1,5]⁴ mom sqrt(Bx²+By²+Bz²)

sinc(z) = sin(z)/z, with sinc(0) = 1.

Source conventions

Definitions follow AI Feynman and the domains in Haider's 2021 preprint, with these explicit choices:

  • I.6.20 uses the two-input Gaussian with denominator sqrt(2 pi) sigma. Haider's preprint prints sqrt(2 pi sigma).
  • I.30.5 uses lambd in [1,2] so all asin arguments are valid.
  • III.9.52 includes the squared sinc denominator from AI Feynman and its continuous limit at equal frequencies.

Data and evaluation

The runner fixes the data seed at 42 and reuses the same noiseless observations across methods and repetitions. Current defaults are 8,000 training, 2,000 validation and 10,000 test rows.

GP fits on training data; HPO uses validation NMSE. Test data score the selected expression and fresh-seed runs of the nominated configuration. Fresh GP seeds measure search variability on the same data.

Run the equation, domain and partition checks from the repository root:

dotnet run --project HyperOp.Checks -c Release