paper-with-me

홈 › Papers

On the Convergence of AdaGrad(Norm) on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration

2022-09-29 · Zijian Liu, Ta Duy Nguyen, Alina Ene, Huy L. Nguyen

Existing analysis of AdaGrad and other adaptive methods for smooth convex optimization is typically for functions with bounded domain diameter. In unconstrained problems, previous works guarantee an asymptotic convergence rate without an explicit constant factor that holds true for the entire function class. Furthermore, in the stochastic setting, only a modified version of AdaGrad, different from the one commonly used in practice, in which the latest gradient is not used to update the stepsize, has been analyzed. Our paper aims at bridging these gaps and developing a deeper understanding of AdaGrad and its variants in the standard setting of smooth convex functions as well as the more general setting of quasar convex functions. First, we demonstrate new techniques to explicitly bound the convergence rate of the vanilla AdaGrad for unconstrained problems in both deterministic and stochastic settings. Second, we propose a variant of AdaGrad for which we can show the convergence of the last iterate, instead of the average iterate. Finally, we give new accelerated adaptive algorithms and their convergence guarantee in the deterministic setting with explicit dependency on the problem parameters, improving upon the asymptotic rate shown in previous works.

📄 PDF Abstract BibTeX arXiv:2209.14827

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…

Similar Papers 제목 키워드 기반

On the Convergence of mSGD and AdaGrad for Stochastic Optimization

2022-01-26 · ICLR 2022 4 · Ruinan Jin, Yu Xing, Xingkang He

As one of the most fundamental stochastic optimization algorithms, stochastic gradient descent (SGD) has been intensively developed and extensively applied in machine learning in the past decade. There have been some mod…

Stochastic Optimization

Stability and convergence analysis of AdaGrad for non-convex optimization via novel stopping time-based techniques

2024-09-08 · Ruinan Jin, Xiaoyu Wang, Baoxiang Wang

Adaptive gradient optimizers (AdaGrad), which dynamically adjust the learning rate based on iterative gradients, have emerged as powerful tools in deep learning. These adaptive methods have significantly succeeded in var…

SADAGRAD: Strongly Adaptive Stochastic Gradient Methods

2018-07-01 · ICML 2018 7 · Zaiyi Chen, Yi Xu, Enhong Chen, Tianbao Yang

Although the convergence rates of existing variants of ADAGRAD have a better dependence on the number of iterations under the strong convexity condition, their iteration complexities have a explicitly linear depende…

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

2024-06-06 · Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov 외

Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the stochastic gradients is heavy-tailed for th…

Stochastic Optimization

AdaGrad stepsizes: Sharp convergence over nonconvex landscapes

2018-06-05 · Rachel Ward, Xiaoxia Wu, Leon Bottou

Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large…

Stochastic Optimization