Machine Learning
26 views
Learning Rate
Quick Definition
Hyperparameter controlling gradient descent step size
Full Definition
A hyperparameter controlling the step size during gradient descent optimization of model parameters.
Examples
training speed, convergence, learning rate scheduling, warmup
Related Terms
gradient-descent
hyperparameter-tuning
More Machine Learning Terms
Gradient Boosting
Sequential ensemble method correcting previous model errors
Gaussian Mixture Model
Probabilistic model using multiple Gaussian distributions
Bagging
Training models on random subsets and averaging predictions
Underfitting
When a model is too simple to capture data patterns
LightGBM
Fast gradient boosting framework using histogram splitting
A/B Testing
Statistical method comparing two versions for performance