More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems
More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems
Fractional-order stochastic gradient descent (FOSGD) leverages fractional exponents to capture long-memory effects in optimization. However, its utility is often limited by the difficulty of tuning and stabilizing these exponents. We propose 2SED Fractional-Order Stochastic Gradient Descent (2SEDFOSGD), which integrates the Two-Scale Effective Dimension (2SED) algorithm with FOSGD to adapt the fractional exponent in a data-driven manner. By tracking model sensitivity and effective dimensionality, 2SEDFOSGD dynamically modulates the exponent to mitigate oscillations and hasten convergence. Theoretically, for onoconvex optimization problems, this approach preserves the advantages of fractional memory without the sluggish or unstable behavior observed in na\"ive fractional SGD. Empirical evaluations in Gaussian and $\alpha$-stable noise scenarios using an autoregressive (AR) model highlight faster convergence and more robust parameter estimates compared to baseline methods, underscoring the potential of dimension-aware fractional techniques for advanced modeling and estimation tasks.
Mohammad Partohaghighi、Roummel Marcia、YangQuan Chen
计算技术、计算机技术自动化基础理论
Mohammad Partohaghighi,Roummel Marcia,YangQuan Chen.More Optimal Fractional-Order Stochastic Gradient Descent for Non-Convex Optimization Problems[EB/OL].(2025-05-05)[2025-06-04].https://arxiv.org/abs/2505.02985.点此复制
评论