Computational Performance

Latency - Bulk vs Atomic Mode

Latency vs Validation Overhead

with sklearn.config_context(assume_finite=True): pass <learning/prediction method here, with reduced validation>

Latency vs Number of Features

Latency vs Input Datatypes

Latency vs Feature Extraction

Example: Model Complexity

Tips - Linear Algebra

Tips - Working Memory Limits

with sklearn.config_context(working_memory=1024): pass <code goes here>

Tips - Model Compression

Tips - Model Reshaping

Example: measure prediction latency, various estimators, bulk vs atomic mode