paper-with-me

Papers

Random-reshuffled SARAH does not need a full gradient computations

2021-11-26 · Aleksandr Beznosikov, Martin Takáč

The StochAstic Recursive grAdient algoritHm (SARAH) algorithm is a variance reduced variant of the Stochastic Gradient Descent (SGD) algorithm that needs a gradient of the objective function from time to time. In this paper, we remove the necessity of a full gradient computation. This is achieved by using a randomized reshuffling strategy and aggregating stochastic gradients obtained in each epoch. The aggregated stochastic gradients serve as an estimate of a full gradient in the SARAH algorithm. We provide a theoretical analysis of the proposed approach and conclude the paper with numerical experiments that demonstrate the efficiency of this approach.

📄 PDF Abstract BibTeX arXiv:2111.13322

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computation

2021-03-02 · Zhize Li, Slavomír Hanzely, Peter Richtárik

We propose ZeroSARAH -- a novel variant of the variance-reduced method SARAH (Nguyen et al., 2017) -- for minimizing the average of a large number of nonconvex functions $\frac{1}{n}\sum_{i=1}^{n}f_i(x)$. To the best of …

Federated Learning

ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computations

2021-09-29 · Zhize Li, Slavomir Hanzely, Peter Richtárik

We propose ZeroSARAH -- a novel variant of the variance-reduced method SARAH (Nguyen et al., 2017) -- for minimizing the average of a large number of nonconvex functions $\frac{1}{n}\sum_{i=1}^{n}f_i(x)$. To the best of …

Federated Learning

SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient

2017-03-01 · ICML 2017 8 · Lam M. Nguyen, Jie Liu, Katya Scheinberg, Martin Takáč

In this paper, we propose a StochAstic Recursive grAdient algoritHm (SARAH), as well as its practical variant SARAH+, as a novel approach to the finite-sum minimization problems. Different from the vanilla SGD and other …

BIG-bench Machine Learning

Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting

2025-06-14 · Duc Toan Nguyen, Trang H. Tran, Lam M. Nguyen

In this paper, we propose Adjusted Shuffling SARAH, a novel algorithm that integrates shuffling techniques with the well-known variance-reduced algorithm SARAH while dynamically adjusting the stochastic gradient weights …

Accelerating Mini-batch SARAH by Step Size Rules

2019-06-20 · Zhuang Yang, Zengping Chen, Cheng Wang

StochAstic Recursive grAdient algoritHm (SARAH), originally proposed for convex optimization and also proven to be effective for general nonconvex optimization, has received great attention due to its simple recursive fr…