kaira.constraints.PeakAmplitudeConstraint

Inheritance diagram of PeakAmplitudeConstraint — Inheritance diagram for PeakAmplitudeConstraint

class kaira.constraints.PeakAmplitudeConstraint(max_amplitude: float, *args, **kwargs)[source]

Bases: BaseConstraint

Enforces maximum signal amplitude by clipping values that exceed threshold.

Limits the maximum amplitude of the signal to prevent clipping in digital-to-analog converters (DACs) and power amplifiers. This constraint applies a hard clipping operation to ensure signal values remain within the specified bounds. Peak amplitude constraints are critical for practical communication systems as discussed in [Armstrong, 2002] and [Jiang and Wu, 2008].

max_amplitude

Maximum allowed amplitude value

Type:: float

Methods

`__init__`	Initialize the peak amplitude constraint.
`forward`	Apply peak amplitude constraint.
`get_dimensions`	Helper method to get all dimensions except batch for calculating norms/means.

__init__(max_amplitude: float, *args, **kwargs) → None[source]

Initialize the peak amplitude constraint.

Parameters:

max_amplitude (float) – Maximum allowed amplitude. Signal values exceeding this threshold (positive or negative) will be clipped.
*args – Variable length argument list.
**kwargs – Arbitrary keyword arguments.

forward(x: Tensor, *args, **kwargs) → Tensor[source]

Apply peak amplitude constraint.

Clips the input signal to ensure all values fall within the range [-max_amplitude, max_amplitude].

Parameters:

x (torch.Tensor) – Input tensor of any shape
*args – Variable length argument list.
**kwargs – Arbitrary keyword arguments.

Returns:

Amplitude-constrained signal with the same shape as input

Return type:

torch.Tensor

static get_dimensions(x: Tensor, exclude_batch: bool = True) → Tuple[int, ...]

Helper method to get all dimensions except batch for calculating norms/means.

Utility function to generate dimension indices for reduction operations like mean or norm. Typically used to calculate signal properties across all dimensions except the batch dimension.

Parameters:

x (torch.Tensor) – Input tensor
exclude_batch (bool, optional) – Whether to exclude the batch dimension (first dimension). Defaults to True.

Returns:

Dimensions to use for reduction operations (e.g., mean, norm)

Return type:

Tuple[int, …]

Example

>>> x = torch.randn(32, 4, 128)  # [batch, antennas, time]
>>> dims = BaseConstraint.get_dimensions(x)
>>> # dims will be (1, 2) for summing across antennas and time