English
Related papers

Related papers: Remove that Square Root: A New Efficient Scale-Inv…

200 papers

In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…

Machine Learning · Computer Science 2022-07-20 Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank J. Reddi , Sanjiv Kumar

Optimizers like Adam and AdaGrad have been very successful in training large-scale neural networks. Yet, the performance of these methods is heavily dependent on a carefully tuned learning rate schedule. We show that in many large-scale…

Machine Learning · Computer Science 2022-02-02 Ehsan Amid , Rohan Anil , Christopher Fifty , Manfred K. Warmuth

From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling…

Machine Learning · Computer Science 2020-03-18 Pedro Savarese , David McAllester , Sudarshan Babu , Michael Maire

In stochastic optimization, a common tool to deal sequentially with large sample is to consider the well-known stochastic gradient algorithm. Nevertheless, since the stepsequence is the same for each direction, this can lead to bad results…

Optimization and Control · Mathematics 2023-03-03 Antoine Godichon-Baggioni , Pierre Tarrago

Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. While adaptive gradient methods theory is well understood for minimization problems, the…

Optimization and Control · Mathematics 2020-12-29 Mingrui Liu , Youssef Mroueh , Jerret Ross , Wei Zhang , Xiaodong Cui , Payel Das , Tianbao Yang

Establishing a fast rate of convergence for optimization methods is crucial to their applicability in practice. With the increasing popularity of deep learning over the past decade, stochastic gradient descent and its adaptive variants…

Optimization and Control · Mathematics 2022-01-03 Adityanarayanan Radhakrishnan , Mikhail Belkin , Caroline Uhler

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 expectation, the squared…

Machine Learning · Statistics 2022-10-18 Alexandre Défossez , Léon Bottou , Francis Bach , Nicolas Usunier

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and…

Machine Learning · Computer Science 2021-08-27 Aaron Defazio , Samy Jelassi

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Machine Learning · Computer Science 2018-04-13 Noam Shazeer , Mitchell Stern

The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD({\lambda}) to data efficient least squares methods. Least square methods make the best use of available data directly…

Artificial Intelligence · Computer Science 2017-03-13 Yangchen Pan , Adam White , Martha White

Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data.…

Machine Learning · Computer Science 2021-02-22 Sharan Vaswani , Issam Laradji , Frederik Kunstner , Si Yi Meng , Mark Schmidt , Simon Lacoste-Julien

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-scale optimization…

Machine Learning · Statistics 2021-04-20 Rachel Ward , Xiaoxia Wu , Leon Bottou

Stochastic optimization algorithms using exponential moving averages of the past gradients, such as ADAM, RMSProp and AdaGrad, have been having great successes in many applications, especially in training deep neural networks. ADAM in…

Machine Learning · Computer Science 2026-01-30 Ruiqi Wang , Diego Klabjan

Adaptive gradient methods have been widely adopted in training large-scale deep neural networks, especially large foundation models. Despite the huge success in practice, their theoretical advantages over classical gradient methods with…

Machine Learning · Computer Science 2024-10-15 Yuxing Liu , Rui Pan , Tong Zhang

Stochastic gradient descent (SGD) has taken the stage as the primary workhorse for large-scale machine learning. It is often used with its adaptive variants such as AdaGrad, Adam, and AMSGrad. This paper proposes an adaptive stochastic…

Machine Learning · Computer Science 2021-01-01 Tianyi Chen , Ziye Guo , Yuejiao Sun , Wotao Yin

We introduce AlphaGrad, a memory-efficient, conditionally stateless optimizer addressing the memory overhead and hyperparameter complexity of adaptive methods like Adam. AlphaGrad enforces scale invariance via tensor-wise L2 gradient…

Machine Learning · Computer Science 2025-04-24 Soham Sane

Since its invention in 2014, the Adam optimizer has received tremendous attention. On one hand, it has been widely used in deep learning and many variants have been proposed, while on the other hand their theoretical convergence property…

Machine Learning · Computer Science 2021-12-08 Zhishuai Guo , Yi Xu , Wotao Yin , Rong Jin , Tianbao Yang

We propose an Adagrad-like algorithm for multi-objective unconstrained optimization that relies on the computation of a common descent direction only. Unlike classical local algorithms for multi-objective optimization, our approach does not…

Optimization and Control · Mathematics 2026-02-06 Marianna De Santis , Gabriele Eichfelder , Margherita Porcelli

This paper presents a novel attention-based algorithm for achieving adaptive computation called DACT, which, unlike existing ones, is end-to-end differentiable. Our method can be used in conjunction with many networks; in particular, we…

Artificial Intelligence · Computer Science 2020-05-25 Cristobal Eyzaguirre , Alvaro Soto

The classical AdaGrad method adapts the learning rate by dividing by the square root of a sum of squared gradients. Because this sum on the denominator is increasing, the method can only decrease step sizes over time, and requires a…

Machine Learning · Computer Science 2022-06-15 Aaron Defazio , Baoyu Zhou , Lin Xiao