BaseEstimator

The abstract base class defining the estimator interface.

Overview

All estimators in Falcon must implement this interface. The base class defines methods for:

• Training (train)
• Sampling (sample_prior, sample_posterior, sample_proposal)
• Persistence (save, load)
• Control flow (pause, resume, interrupt)

Class Reference

BaseEstimator

Bases: ABC

Fully abstract base class defining the estimator interface.

All methods are abstract - no implementation details. Concrete implementations must provide all functionality.

Conditions are passed as Dict[str, Tensor] mapping node names to values. Sampling methods return dicts with 'value' (ndarray) and optionally 'log_prob' (ndarray).

train abstractmethod async

train(buffer)

Train the estimator.

Parameters:

Name	Type	Description	Default
buffer		BufferView providing access to training/validation data	required

Source code in falcon/core/base_estimator.py

@abstractmethod
async def train(self, buffer) -> None:
    """
    Train the estimator.

    Args:
        buffer: BufferView providing access to training/validation data
    """
    pass

sample_prior abstractmethod

sample_prior(num_samples, conditions=None)

Sample from the prior distribution.

Parameters:

Name	Type	Description	Default
num_samples	int	Number of samples to generate	required
conditions	Optional[Conditions]	Conditioning values from parent nodes (usually None for prior)	None

Returns:

Type	Description
dict	Dict with 'value' (ndarray) and optionally 'log_prob' (ndarray)

Source code in falcon/core/base_estimator.py

@abstractmethod
def sample_prior(
    self, num_samples: int, conditions: Optional[Conditions] = None
) -> dict:
    """
    Sample from the prior distribution.

    Args:
        num_samples: Number of samples to generate
        conditions: Conditioning values from parent nodes (usually None for prior)

    Returns:
        Dict with 'value' (ndarray) and optionally 'log_prob' (ndarray)
    """
    pass

sample_posterior abstractmethod

sample_posterior(num_samples, conditions=None)

Sample from the posterior distribution.

Parameters:

Name	Type	Description	Default
num_samples	int	Number of samples to generate	required
conditions	Optional[Conditions]	Dict mapping node names to condition tensors	None

Returns:

Type	Description
dict	Dict with 'value' (ndarray) and optionally 'log_prob' (ndarray)

Source code in falcon/core/base_estimator.py

@abstractmethod
def sample_posterior(
    self, num_samples: int, conditions: Optional[Conditions] = None
) -> dict:
    """
    Sample from the posterior distribution.

    Args:
        num_samples: Number of samples to generate
        conditions: Dict mapping node names to condition tensors

    Returns:
        Dict with 'value' (ndarray) and optionally 'log_prob' (ndarray)
    """
    pass

sample_proposal abstractmethod

sample_proposal(num_samples, conditions=None)

Sample from the proposal distribution for adaptive resampling.

Parameters:

Name	Type	Description	Default
num_samples	int	Number of samples to generate	required
conditions	Optional[Conditions]	Dict mapping node names to condition tensors	None

Returns:

Type	Description
dict	Dict with 'value' (ndarray) and optionally 'log_prob' (ndarray)

Source code in falcon/core/base_estimator.py

@abstractmethod
def sample_proposal(
    self, num_samples: int, conditions: Optional[Conditions] = None
) -> dict:
    """
    Sample from the proposal distribution for adaptive resampling.

    Args:
        num_samples: Number of samples to generate
        conditions: Dict mapping node names to condition tensors

    Returns:
        Dict with 'value' (ndarray) and optionally 'log_prob' (ndarray)
    """
    pass

save abstractmethod

save(node_dir)

Save estimator state to directory.

Parameters:

Name	Type	Description	Default
node_dir	Path	Directory to save state to	required

Source code in falcon/core/base_estimator.py

@abstractmethod
def save(self, node_dir: Path) -> None:
    """
    Save estimator state to directory.

    Args:
        node_dir: Directory to save state to
    """
    pass

load abstractmethod

load(node_dir)

Load estimator state from directory.

Parameters:

Name	Type	Description	Default
node_dir	Path	Directory to load state from	required

Source code in falcon/core/base_estimator.py

@abstractmethod
def load(self, node_dir: Path) -> None:
    """
    Load estimator state from directory.

    Args:
        node_dir: Directory to load state from
    """
    pass

pause abstractmethod

pause()

Pause training loop.

Source code in falcon/core/base_estimator.py

@abstractmethod
def pause(self) -> None:
    """Pause training loop."""
    pass

resume abstractmethod

resume()

Resume training loop.

Source code in falcon/core/base_estimator.py

@abstractmethod
def resume(self) -> None:
    """Resume training loop."""
    pass

interrupt abstractmethod

interrupt()

Terminate training loop.

Source code in falcon/core/base_estimator.py

@abstractmethod
def interrupt(self) -> None:
    """Terminate training loop."""
    pass