Isolation Forest follow-up work

[csadorf]

Tracks deferred robustness, scalability, interoperability, API-parity, and cuml.accel work following #8226.

C++ API robustness

• Handle n_rows == 0 in the public C++ scoring path before launching a zero-block CUDA kernel, and use checked launch-dimension casts. Isolation Forest Implementation  #8226 (comment)

Sampling quality and scalability

• Avoid the linear duplicate checks used for row and feature sampling at large max_samples or max_features. Consider a fast path when max_samples == n_rows and a scalable sampling strategy. Isolation Forest Implementation  #8226 (comment)
• Select uniformly among nonconstant features when splitting a node, avoiding sensitivity to column order. Isolation Forest Implementation  #8226 (comment)

Python interoperability and persistence

• Support conversion of fitted models between cuML and scikit-learn, or document any representations that cannot be transferred. Isolation Forest Implementation  #8226 (comment)
• Investigate using nvforest for inference, and dropping the C++ model entirely
• Preserve fitted model behavior across pickle round trips, potentially using the serialized Treelite model and nvForest inference path, and remove the check_estimators_pickle xfail.
• Raise NotFittedError from unfitted estimator methods and remove the corresponding common-estimator-check xfail.
• Implement or deprecate the unsupported sample_weight argument
• Implement or deprecate the unsupported warm_start argument
• Support estimator_, estimators_, estimators_features_, and estimators_samples_ attributes

cuml.accel support

• Add cuml.accel support for IsolationForest.

Treelite usage

• Set task_type=kIsolationForest in the Treelite representation
• Use the built-in postprocessor exponential_standard_ratio in Treelite/nvForest; remove the transform s(x) = 2^(-E[h(x)] / c(n)) from the Python layer.

Follow-up to #8226.
Related to #6096.