Results for "efficiency"
Batch Size
Intermediate
Number of samples per gradient update; impacts compute efficiency, generalization, and stability.
Vocabulary
Intermediate
The set of tokens a model can represent; impacts efficiency, multilinguality, and handling of rare strings.
Pruning
Intermediate
Removing weights or neurons to shrink models and improve efficiency; can be structured or unstructured.
Distillation
Intermediate
Training a smaller “student” model to mimic a larger “teacher,” often improving efficiency while retaining performance.
Inductive Bias
Intermediate
Built-in assumptions guiding learning efficiency and generalization.
Latent Diffusion
Advanced
Diffusion performed in latent space for efficiency.