Skip to main content

omnibias.core

The backend-agnostic mathematical core. No framework dependencies — every backend imports these symbols, which is what makes results bit-identical.

import omnibias.core as oc

Polynomial coefficients

The recurrences behind the closed-form derivative tower.

SymbolMeaning
sigmoid_polynomial_coeffsEulerian recurrence: σⁿ(z) = Pₙ(sigmoid(z))
tanh_polynomial_coeffsLegendre-style recurrence: tanhⁿ(z) = Tₙ(tanh(z))
hermite_coeffsprobabilist's Hermite coefficients for the Gaussian tower

Bell polynomials / Faà di Bruno

The combinatorics of differentiating compositions — the engine under jets.

SymbolMeaning
bell_partialpartial (incomplete) Bell polynomial
bell_completecomplete Bell polynomial
bell_numberBell number
faa_di_bruno_termsthe Faà di Bruno decomposition terms

Multi-index combinatorics

Bookkeeping for multivariate jets.

multi_indices · multiply_table · multi_index_factorial · index_position · num_multi_indices

The activation protocol

SymbolMeaning
ActivationSpecgeneric activation descriptor backends specialize
NthDerivativeFn, TensorFn, TensorTtyping aliases for the protocol

Moments, information, probability helpers

Backend-agnostic statistical utilities used by the GLM / uncertainty surfaces:

  • moments: central_moments_from_cumulants, cumulants_from_raw_moments, raw_moments_from_cumulants, gaussian_central_moments, delta_method_central_moments, second_order_delta, …
  • information: binary_entropy, has_cumulant_tower, is_log_partition_activation.
  • probability: cdf_normalization, dkw_epsilon, is_cdf_activation.
The rigorous & formal layers

omnibias.core.verified (intervals, affine, Taylor models, Lohner flow) and omnibias.core.proof (certificate format + Lean bridge) are part of core but documented in the architecture section: certified register and formal loop.

See also