Towards stability and optimality in stochastic gradient descent
원문 초록
Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are statistically inefficient as estimators of the true parameter value. To address these two issues, we propose a new iterative procedure termed averaged implicit SGD (AI-SGD). For statistical efficiency, AI-SGD employs averaging of the iterates, which achieves the optimal Cram\'{e}r-Rao bound under strong convexity, i.e., it is an optimal unbiased estimator of the true parameter value. For numerical stability, AI-SGD employs an implicit update at each iteration, which is related to proximal operators in optimization. In practice, AI-SGD achieves competitive performance with other state-of-the-art procedures. Furthermore, it is more stable than averaging procedures that do not employ proximal updates, and is simple to implement as it requires fewer tunable hyperparameters than procedures that do employ proximal updates.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots
Analytic estimation of parameters of stochastic volatility diffusion models with exponential-affine characteristic function for currency option pricing
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
Robust Spatiotemporal Epidemic Modeling with Integrated Adaptive Outlier Detection
IMC-PINN-FE: A Physics-Informed Neural Network for Patient-Specific Left Ventricular Finite Element Modeling with Image Motion Consistency and Biomechanical Parameter Estimation
Adjustment for Confounding using Pre-Trained Representations
토론
이 논문과 연결된 포럼 글이 아직 없습니다.