השוואת שיטות

	פרטיות דיפרנציאלית	זיקוק ידע (Knowledge Distillation)	ירידה סטוכסטית של גרדיאנט (SGD)
תחום	פרטיות	למידה עמוקה	למידת מכונה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	2006	2015	1951
הוגה השיטה	Cynthia Dwork	Hinton, G., Vinyals, O. & Dean, J.	Robbins, H. & Monro, S.
סוג	Privacy-preserving randomized mechanism	Neural network compression (teacher–student)	First-order iterative optimization algorithm
מקור מכונן	Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12.	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.
כינויים	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
קשורות	3	5	3
תקציר	Differential privacy is a mathematical framework for releasing statistical information about a dataset while providing rigorous guarantees that individual records cannot be identified or inferred. Introduced by Cynthia Dwork in 2006, it formalizes privacy as a probabilistic bound: any single individual's presence or absence in the dataset changes the output distribution by at most a multiplicative factor of e^ε, where ε is the privacy budget controlling the privacy–utility tradeoff.	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.