nnpiv.linear.L2OptimisticHedgeVsOGD

class nnpiv.linear.L2OptimisticHedgeVsOGD(lambda_theta=0.01, B=100, eta_theta='auto', eta_w='auto', n_iter=2000, tol=0.01, sparsity=None, fit_intercept=True)

Optimistic Hedge learner against projected gradient ascent.

The optimistic critic update uses the immediately preceding moment score. Returned coefficients and critic weights average the feasible iterates.

fit(Z, X, Y)

Fit.

Parameters

• Z (array-like) – Instrumental variables.

• X (array-like) – Feature or treatment matrix.

• Y (array-like) – Outcome values.

predict(X)

Predict.

Parameters

X (array-like) – Feature or treatment matrix.

Returns

Fitted linear function evaluated at X.

Return type

ndarray