Enhancing Stochastic Gradient Descent: A Unified Framework and Novel Acceleration Methods for Faster Convergence
CoRR(2024)
摘要
Based on SGD, previous works have proposed many algorithms that have improved
convergence speed and generalization in stochastic optimization, such as SGDm,
AdaGrad, Adam, etc. However, their convergence analysis under non-convex
conditions is challenging. In this work, we propose a unified framework to
address this issue. For any first-order methods, we interpret the updated
direction g_t as the sum of the stochastic subgradient ∇ f_t(x_t) and
an additional acceleration term 2|⟨ v_t, ∇ f_t(x_t)
⟩|/v_t_2^2 v_t, thus we can discuss the convergence by analyzing
⟨ v_t, ∇ f_t(x_t) ⟩. Through our framework, we have
discovered two plug-and-play acceleration methods: Reject Accelerating
and Random Vector Accelerating, we theoretically demonstrate that
these two methods can directly lead to an improvement in convergence rate.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要