bayespecon.logdet.flow_logdet_pytensor¶
-
bayespecon.logdet.flow_logdet_pytensor(rho_d, rho_o, rho_w, poly_a, poly_b, poly_c, poly_coeffs, miter_a, miter_b, miter_c, miter_coeffs, miter, titer=
800)[source]¶ Differentiable PyTensor log-determinant for the flow SAR model.
Evaluates
\[\log|I_N - \rho_d W_d - \rho_o W_o - \rho_w W_w|\]as a fully differentiable PyTensor expression suitable for use as
pm.Potential("jacobian", flow_logdet_pytensor(...)).The computation has two parts:
Polynomial part (orders 1 to miter): vectorised sum over precomputed
(a, b, c, coeff)triples — no Python loop at evaluation time.Geometric tail (orders miter+1 to titer): closed-form sum using the upper-bound approximation \(\text{tr}(W_F^k) \approx s^{k-m} \cdot \text{tr}(W_F^m)\) where \(s = \rho_d + \rho_o + \rho_w\) is the spectral-radius bound for row-stochastic W, following
fodet1.mlines 60–70.
- Parameters:¶
- rho_d¶
PyTensor scalar variables for the three spatial parameters.
- rho_o¶
PyTensor scalar variables for the three spatial parameters.
- rho_w¶
PyTensor scalar variables for the three spatial parameters.
- poly_a¶
Precomputed exponent arrays and coefficients for the polynomial part, from
_flow_logdet_poly_coeffs().- poly_b¶
Precomputed exponent arrays and coefficients for the polynomial part, from
_flow_logdet_poly_coeffs().- poly_c¶
Precomputed exponent arrays and coefficients for the polynomial part, from
_flow_logdet_poly_coeffs().- poly_coeffs¶
Precomputed exponent arrays and coefficients for the polynomial part, from
_flow_logdet_poly_coeffs().- miter_a¶
Exponents and trace-product weights for the highest-order polynomial terms (k = miter), used to compute
tr(W_F^miter)symbolically for the geometric tail.- miter_b¶
Exponents and trace-product weights for the highest-order polynomial terms (k = miter), used to compute
tr(W_F^miter)symbolically for the geometric tail.- miter_c¶
Exponents and trace-product weights for the highest-order polynomial terms (k = miter), used to compute
tr(W_F^miter)symbolically for the geometric tail.- miter_coeffs¶
Exponents and trace-product weights for the highest-order polynomial terms (k = miter), used to compute
tr(W_F^miter)symbolically for the geometric tail.- miter : int¶
Highest polynomial order included in the exact series.
- titer : int, default=800¶
Highest order included in the geometric tail approximation.
- Returns:¶
Scalar log-determinant expression.
- Return type:¶