quantdata.dysanos.grid.rndysanos.quadratic_action#

Regularized conditional-action objectives for drift diagnostics.

This module deliberately does not construct a risk-neutral density. For

Y = a(z)' dH - kappa * ||a(z)||**2

is evaluated through the optimized-certainty-equivalent objective

sup_{a,y} E[u(Y+y)-y].

the first-order condition is

E[u'(Y) * (dH - 2*kappa*a(z)) | z] = 0.

Here the OCE first-order condition in y normalizes marginal utility to one. The action condition consequently leaves conditional drift 2*kappa*a(z) under that marginal-utility density rather than zero. The quadratic term makes the optimization coercive and is useful for learning conditional drift without relying on an output cap.

class quantdata.dysanos.grid.rndysanos.quadratic_action.DirectActionNetwork(env, *, num_input, num_output, config)[source]#

Bases: BaseModel

Unbounded feed-forward action with a neutral zero initialization.

zero_output_layer()[source]#

Set the last affine map to zero without changing hidden features.

forward(z)[source]#

Forward method.

Parameters:
  • data (dict) – Input data dictionary containing tensors for the model. The expected keys and tensor shapes depend on the specific model implementation.

  • training (bool, default False) – Whether the model is in training mode.

  • return_what (BaseModel.ReturnWhat, default ReturnWhat.LOSS_WEIGHT) – Specifies what the model should return. Options are: - ReturnWhat.LOSS_WEIGHT: return float loss (with gradient) and float weight (without gradient) for training. - ReturnWhat.VALUATION: return loss, weight and a dictionary of additional float metrics. - ReturnWhat.PATHWISE: return pathwise metrics as dictionary.

class quantdata.dysanos.grid.rndysanos.quadratic_action.QuadraticActionConfig(*, utility='entropy', lmbda=1.0, downside_power=2, quadratic_coefficient=0.5, bounded_action=False, initial_action_scale=1.0, network_config=FeedForwardConfig(activation='LeakyReLU', num_depth=2, num_width=100, use_bias=True))[source]#

Bases: object

Logical configuration of the regularized action experiment.

utility: str = 'entropy'#
lmbda: float = 1.0#
downside_power: int = 2#
quadratic_coefficient: float = 0.5#
bounded_action: bool = False#
initial_action_scale: float = 1.0#
network_config: FeedForwardConfig = FeedForwardConfig(activation='LeakyReLU', num_depth=2, num_width=100, use_bias=True)#
class quantdata.dysanos.grid.rndysanos.quadratic_action.QuadraticActionModel(env, *, num_input, num_instruments, config)[source]#

Bases: BaseModel

Conditional portfolio with a quadratic position charge inside utility.

outputs(data)[source]#
forward(data)[source]#

Forward method.

Parameters:
  • data (Mapping[str, Tensor]) – Input data dictionary containing tensors for the model. The expected keys and tensor shapes depend on the specific model implementation.

  • training (bool, default False) – Whether the model is in training mode.

  • return_what (BaseModel.ReturnWhat, default ReturnWhat.LOSS_WEIGHT) – Specifies what the model should return. Options are: - ReturnWhat.LOSS_WEIGHT: return float loss (with gradient) and float weight (without gradient) for training. - ReturnWhat.VALUATION: return loss, weight and a dictionary of additional float metrics. - ReturnWhat.PATHWISE: return pathwise metrics as dictionary.

quantdata.dysanos.grid.rndysanos.quadratic_action.conditional_gaussian_entropy_action(mean, covariance, *, lmbda, quadratic_coefficient)[source]#

Return (2*kappa*I + lambda*Sigma)^{-1} mean.

quantdata.dysanos.grid.rndysanos.quadratic_action.downside_oce_utility(x, y, *, scale, power)[source]#

Return -scale*(-(x+y))_+**power-y and its derivative in x.

quantdata.dysanos.grid.rndysanos.quadratic_action.iter_path_batches(data, batch_size)[source]#

Yield complete-path batches without changing any within-path reduction.

quantdata.dysanos.grid.rndysanos.quadratic_action.objective_gradient(model, data, *, batch_size)[source]#

Differentiate the exact full-split empirical objective in path batches.

quantdata.dysanos.grid.rndysanos.quadratic_action.parameter_norm(parameters)[source]#

Return the finite Euclidean norm of a parameter sequence.

quantdata.dysanos.grid.rndysanos.quadratic_action.valuate_quadratic_action(model, data, *, batch_size)[source]#

Return saturation, first-order, and induced-density diagnostics.