FlexMF Explicit

This page analyzes the hyperparameter tuning results for the FlexMF scorer in explicit-feedback mode (a biased matrix factorization model trained with PyTorch).

Parameter Search Space

Parameter	Type	Distribution	Values	Selected
embedding_size	Integer	LogUniform	4 ≤ \(x\) ≤ 512	14
regularization	Float	LogUniform	0.0001 ≤ \(x\) ≤ 10	0.0498
learning_rate	Float	LogUniform	0.001 ≤ \(x\) ≤ 0.1	0.0025
reg_method	Categorical	Uniform	L2, AdamW	L2

Final Result

Searching selected the following configuration:

{
    'embedding_size': 14,
    'regularization': 0.04977041557904842,
    'learning_rate': 0.002501599473184507,
    'reg_method': 'L2',
    'epochs': 6
}

With these metrics:

{
    'RBP': 0.11807363051215715,
    'NDCG': 0.37717426296763396,
    'RecipRank': 0.2592344438170556,
    'RMSE': 0.7829963558088198,
    'TrainTask': 'ed8b825b-c5b4-4ace-b605-1924db72f19f',
    'TrainTime': None,
    'TrainCPU': None,
    'max_epochs': 50,
    'done': True,
    'training_iteration': 6,
    'trial_id': '921a5_00065',
    'date': '2025-04-22_15-52-28',
    'timestamp': 1745351548,
    'time_this_iter_s': 16.80943536758423,
    'time_total_s': 102.95551085472107,
    'pid': 949868,
    'hostname': 'CCI-ws21',
    'node_ip': '10.248.127.152',
    'config': {
        'embedding_size': 14,
        'regularization': 0.04977041557904842,
        'learning_rate': 0.002501599473184507,
        'reg_method': 'L2',
        'epochs': 6
    },
    'time_since_restore': 102.95551085472107,
    'iterations_since_restore': 6
}

Parameter Analysis

Embedding Size

The embedding size is the hyperparameter that most affects the model’s fundamental logic, so let’s look at performance as a fufnction of it:

Iteration Completion

How many iterations, on average, did we complete?

How did the metric progress in the best result?

How did the metric progress in the longest results?