Comparer des méthodes

	Distillation de connaissances	Descente de gradient stochastique (SGD)
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2015	1951
Auteur d'origine	Hinton, G., Vinyals, O. & Dean, J.	Robbins, H. & Monro, S.
Type	Neural network compression (teacher–student)	First-order iterative optimization algorithm
Source fondatrice	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), 400–407.
Alias	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
Apparentées	5	3
Résumé	Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.	Stochastic Gradient Descent (SGD) is a first-order iterative optimization algorithm, rooted in the stochastic approximation framework introduced by Robbins and Monro in 1951, that minimizes an objective function by updating model parameters using the gradient computed on a single randomly selected training example (or a small mini-batch) at each step. It is the core optimization engine behind modern machine learning and deep learning, enabling the training of models on datasets too large to fit in memory.