paper-with-me

홈 › Papers

Generalized AdaGrad (G-AdaGrad) and Adam: A State-Space Perspective

2021-05-31 · Kushal Chakrabarti, Nikhil Chopra

Accelerated gradient-based methods are being extensively used for solving non-convex machine learning problems, especially when the data points are abundant or the available data is distributed across several agents. Two of the prominent accelerated gradient algorithms are AdaGrad and Adam. AdaGrad is the simplest accelerated gradient method, which is particularly effective for sparse data. Adam has been shown to perform favorably in deep learning problems compared to other methods. In this paper, we propose a new fast optimizer, Generalized AdaGrad (G-AdaGrad), for accelerating the solution of potentially non-convex machine learning problems. Specifically, we adopt a state-space perspective for analyzing the convergence of gradient acceleration algorithms, namely G-AdaGrad and Adam, in machine learning. Our proposed state-space models are governed by ordinary differential equations. We present simple convergence proofs of these two algorithms in the deterministic settings with minimal assumptions. Our analysis also provides intuition behind improving upon AdaGrad's convergence rate. We provide empirical results on MNIST dataset to reinforce our claims on the convergence and performance of G-AdaGrad and Adam.

📄 PDF Abstract BibTeX arXiv:2106.00092

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningState Space Models

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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad

2024-03-05 · Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horvath 외

Adaptive methods are extremely popular in machine learning as they make learning rate tuning less expensive. This paper introduces a novel optimization algorithm named KATE, which presents a scale-invariant adaptation of…

image-classificationImage Classificationtext-classificationText Classification

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

Towards Simple and Provable Parameter-Free Adaptive Gradient Methods

2024-12-27 · Yuanzhe Tao, Huizhuo Yuan, Xun Zhou, Yuan Cao 외

Optimization algorithms such as AdaGrad and Adam have significantly advanced the training of deep models by dynamically adjusting the learning rate during the optimization process. However, adhoc tuning of learning rates…

A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration

2018-08-10 · Li Shen, Congliang Chen, Fangyu Zou, Zequn Jie 외

Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as AdaGrad, RMSProp, Adam, AccAdaGrad, \textit{etc}. In spite of …

Stochastic Optimization

A Simple Convergence Proof of Adam and Adagrad

2020-03-05 · Alexandre Défossez, Léon Bottou, Francis Bach, Nicolas Usunier

We provide a simple proof of convergence covering both the Adam and Adagrad adaptive optimization algorithms when applied to smooth (possibly non-convex) objective functions with bounded gradients. We show that in expect…