방법 비교

	베이지안 최적화	신경망 구조 탐색	확률적 최적화
분야	최적화	딥러닝	최적화
계열	Process / pipeline	Machine learning	Process / pipeline
기원 연도	1975 (foundational); 2012 (ML standard)	2017	1951 (SGD); 2014 (Adam)
창시자	Mockus (1975); popularised for ML by Snoek, Larochelle & Adams (2012)	Zoph, B. & Le, Q.V.	—
유형	Sequential model-based black-box optimization	Automated architecture optimization (deep learning)	Gradient-based iterative optimization
원전	Snoek, J., Larochelle, H., & Adams, R.P. (2012). Practical Bayesian Optimization of Machine Learning Algorithms. Advances in Neural Information Processing Systems (NeurIPS), 25.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. Annals of Mathematical Statistics, 22(3), 400-407.
별칭	Bayesçi Optimizasyon (Hyperparameter Tuning), surrogate-based optimization, sequential model-based optimization, SMBO	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	Stokastik Optimizasyon (SGD & Varyantları), stochastic gradient descent, SGD, Adam
관련	2	5	3
요약	Bayesian Optimization is a sequential, model-based strategy for finding the optimum of expensive black-box functions with as few evaluations as possible. Rooted in the work of Mockus (1975) and brought to mainstream machine-learning practice by Snoek, Larochelle, and Adams (2012), it fits a probabilistic surrogate model — typically a Gaussian Process — to past observations and uses an acquisition function to decide where to probe next, balancing exploration of unknown regions with exploitation of promising ones.	Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.	Stochastic optimization is a family of iterative methods that minimize an objective function by computing gradients on randomly sampled subsets of data — mini-batches — rather than on the entire dataset at once. Pioneered by Robbins and Monro in 1951 as stochastic approximation, the approach became the standard engine for training large-scale machine-learning models through variants such as SGD with momentum, AdaGrad, RMSProp, and Adam.