This page analyzes the hyperparameter tuning results for the FlexMF scorer in implicit-feedback mode with logistic loss (Logistic Matrix Factorization).
Parameter Search Space
/home/mde48/lenskit/lenskit-codex/.venv/lib/python3.12/site-packages/ray/tune/search/sample.py:700: RayDeprecationWarning: The `base` argument is deprecated. Please remove it as it is not actually needed in this method.
embedding_size |
Integer |
LogUniform |
4 ≤ \(x\) ≤ 512 |
30 |
regularization |
Float |
LogUniform |
0.0001 ≤ \(x\) ≤ 10 |
0.0658 |
learning_rate |
Float |
LogUniform |
0.001 ≤ \(x\) ≤ 0.1 |
0.00339 |
reg_method |
Categorical |
Uniform |
L2, AdamW |
AdamW |
negative_count |
Integer |
Uniform |
1 ≤ \(x\) ≤ 5 |
4 |
positive_weight |
Float |
Uniform |
1 ≤ \(x\) ≤ 10 |
6.79 |
user_bias |
Categorical |
Uniform |
True, False |
False |
item_bias |
Categorical |
Uniform |
True, False |
True |
Final Result
Searching selected the following configuration:
{
'embedding_size': 30,
'regularization': 0.06582019563774084,
'learning_rate': 0.003392744782918509,
'reg_method': 'AdamW',
'negative_count': 4,
'positive_weight': 6.793432608396559,
'user_bias': False,
'item_bias': True,
'epochs': 14
}
With these metrics:
{
'RBP': 0.2117583124736642,
'LogRBP': 2.2419302796252634,
'NDCG': 0.4518275158182063,
'RecipRank': 0.39610287024847396,
'TrainTask': 'bac615ca-8038-4369-9e53-d82fbcfd8761',
'TrainTime': None,
'TrainCPU': None,
'max_epochs': 50,
'done': False,
'training_iteration': 14,
'trial_id': 'c6732d90',
'date': '2025-05-05_22-14-14',
'timestamp': 1746497654,
'time_this_iter_s': 39.01932764053345,
'time_total_s': 392.05819034576416,
'pid': 383329,
'hostname': 'CCI-ws21',
'node_ip': '10.248.127.152',
'config': {
'embedding_size': 30,
'regularization': 0.06582019563774084,
'learning_rate': 0.003392744782918509,
'reg_method': 'AdamW',
'negative_count': 4,
'positive_weight': 6.793432608396559,
'user_bias': False,
'item_bias': True,
'epochs': 14
},
'time_since_restore': 68.3108901977539,
'iterations_since_restore': 2
}
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?