bijx.Bijection¶
- class bijx.Bijection[source]¶
Bases:
Module
Base class for all bijective transformations.
A bijection represents an invertible mapping between two spaces, equipped with forward and reverse transformations that properly track log-density changes according to the change of variables formula.
Note
This is an abstract base class. Subclasses must override forward() and reverse() methods to implement the actual transformation logic.
- __init__(*args, **kwargs)¶
Methods
forward
(x, log_density, **kwargs)Apply forward transformation.
invert
()Create an inverted version of this bijection.
reverse
(x, log_density, **kwargs)Apply reverse (inverse) transformation.
- forward(x, log_density, **kwargs)[source]¶
Apply forward transformation.
Transforms input through the bijection and updates log-density according to the change of variables formula.
For convenience
Bijection()
gives the default identity bijection.- Parameters:
x – Input data of any pytree structure.
log_density – Log density values corresponding to the input.
**kwargs – Additional transformation-specific arguments.
- Returns:
Tuple of (transformed_data, updated_log_density) where the log-density incorporates the log absolute determinant of the transformation Jacobian.
- reverse(x, log_density, **kwargs)[source]¶
Apply reverse (inverse) transformation.
Transforms input through the inverse bijection and updates log-density accordingly.
- Parameters:
x – Input data of any pytree structure.
log_density – Log density values corresponding to the input.
**kwargs – Additional transformation-specific arguments.
- Returns:
Tuple of (inverse_transformed_data, updated_log_density) where the log-density change has the opposite sign compared to forward().