Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
Moscow Institute of Physics and Technology, Russia（莫斯科物理技术学院）；Ivannikov Institute for System Programming RAS, Russia（伊万诺夫系统编程研究所）；Sber AI Lab, Russia（俄罗斯Sber人工智能实验室）；Innopolis University, Russia（因诺波利斯大学）；The Russian Presidential Academy of National Economy and Public Administration, Russia（俄罗斯总统经济与公共行政学院）；Skolkovo Institute of Science and Technology, Russia（斯克沃尔佐夫科学与技术研究所）；Mohamed bin Zayed University of Artificial Intelligence, UAE（穆罕默德·本·扎耶德人工智能大学）；Machine Learning and Optimization Laboratory (MLO), EPFL, Lausanne, Switzerland（机器学习与优化实验室（MLO），EPFL，拉瓦尔普勒斯，瑞士）
Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, Aleksandr Beznosikov, Alexander Gasnikov, Samuel Horváth, Martin Takáč, Eduard Gorbunov
备注：
ICML 2025. 65 pages, 12 figures. Changes in V3: extended results for the methods with coordinate-wise stepsizes and new experiments
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 the later ones. Gradient clipping provably helps to achieve good high-probability convergence for such noises. However, despite the similarity between AdaGrad/Adam and Clip-SGD, the current understanding of the high-probability convergence of AdaGrad/Adam-type methods is limited in this case. In this work, we prove that AdaGrad/Adam (and their delayed version) can have provably bad high-probability convergence if the noise is heavy-tailed. We also show that gradient clipping fixes this issue, i.e., we derive new high-probability convergence bounds with polylogarithmic dependence on the confidence level for AdaGrad-Norm and Adam-Norm with clipping and with/without delay for smooth convex/non-convex stochastic optimization with heavy-tailed noise. We extend our results to the case of AdaGrad/Adam with delayed stepsizes. Our empirical evaluations highlight the superiority of clipped versions of AdaGrad/Adam in handling the heavy-tailed noise.
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 norm of the objective gradient averaged over the trajectory has an upper-bound which is explicit in the constants of the problem, parameters of the optimizer, the dimension $d$, and the total number of iterations $N$. This bound can be made arbitrarily small, and with the right hyper-parameters, Adam can be shown to converge with the same rate of convergence …
Towards Simple and Provable Parameter-Free Adaptive Gradient Methods
School of Mathematical Sciences, Peking University（北京大学数学科学学院）；Department of Computer Science, University of California, Los Angeles（加州大学洛杉矶分校计算机科学系）；School of Computing and Data Science, the University of Hong Kong（香港大学计算科学与数据科学学院）；Bytedance Inc（字节跳动公司）
提出 AdaGrad++ 和 Adam++ 两种简单无参数自适应梯度方法，在无需预设学习率的情况下实现与 AdaGrad 和 Adam 相当的收敛保证。
University of Science and Technology of China（中国科学技术大学）；Zhejiang Cainiao Supply Chain Management Co. Ltd（浙江菜鸟供应链管理有限公司）；Advanced Digital Sciences Center（先进数字科学中心）
Adaptive learning rate methods have been successfully applied in many fields, especially in training deep neural networks. Recent results have shown that adaptive methods with exponential increasing weights on squared past gradients (i.e., ADAM, RMSPROP) may fail to converge to the optimal solution. Though many algorithms, such as AMSGRAD and ADAMNC, have been proposed to fix the non-convergence issues, achieving a data-dependent regret bound similar to or better than ADAGRAD is still a challenge to these methods. In this paper, we propose a novel adaptive method weighted adaptive algorithm (W…
George Mason University（乔治梅森大学）；Boston University（波士顿大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Traditional analyses in non-convex optimization typically rely on the smoothness assumption, namely requiring the gradients to be Lipschitz. However, recent evidence shows that this smoothness condition does not capture the properties of some deep learning objective functions, including the ones involving Recurrent Neural Networks and LSTMs. Instead, they satisfy a much more relaxed condition, with potentially unbounded smoothness. Under this relaxed assumption, it has been theoretically and empirically shown that the gradient-clipped SGD has an advantage over the vanilla one. In this paper, w…
Despite superior training outcomes, adaptive optimization methods such as Adam, Adagrad or RMSprop have been found to generalize poorly compared to Stochastic gradient descent (SGD). These methods tend to perform well in the initial portion of training but are outperformed by SGD at later stages of training. We investigate a hybrid strategy that begins training with an adaptive method and switches to SGD when appropriate. Concretely, we propose SWATS, a simple strategy which switches from Adam to SGD when a triggering condition is satisfied. The condition we propose relates to the projection o…
Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of California, Los Angeles（加州大学洛杉矶分校）
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 gradient descent method for distributed machine learning, which can be viewed as the communication-adaptive counterpart of the celebrated Adam method - justifying its name CADA. The key components of CADA are a set of new rules tailored for adaptive stochastic gradients that can be implemented to save communication upload. The new algorithms adaptively reuse the…
A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning
Division of Data and Decision Sciences（数据与决策科学部）；Tata Consultancy Services Research（塔塔咨询服务公司研究院）；University of Maryland（马里兰大学）；Department of Mechanical Engineering（机械工程系）
本文基于状态空间建模与控制理论传递函数提出自适应梯度优化通用框架及 Adam 新变体 AdamSSM，证明其收敛性，并在图像分类和语言建模任务上验证其泛化与收敛优势。
Changchun University of Science and Technology（长春理工大学）；Northeast Normal University（东北师范大学）
Adaptive gradient algorithm (AdaGrad) and its variants, such as RMSProp, Adam, AMSGrad, etc, have been widely used in deep learning. Although these algorithms are faster in the early phase of training, their generalization performance is often not as good as stochastic gradient descent (SGD). Hence, a trade-off method of transforming Adam to SGD after a certain iteration to gain the merits of both algorithms is theoretically and practically significant. To that end, we propose a decreasing scaling transition scheme to achieve a smooth and stable transition from Adam to SGD, which is called DST…
Stanford University（斯坦福大学）；Apple（苹果公司）；Massachusetts Institute of Technology（麻省理工学院）
We study adaptive methods for differentially private convex optimization, proposing and analyzing differentially private variants of a Stochastic Gradient Descent (SGD) algorithm with adaptive stepsizes, as well as the AdaGrad algorithm. We provide upper bounds on the regret of both algorithms and show that the bounds are (worst-case) optimal. As a consequence of our development, we show that our private versions of AdaGrad outperform adaptive SGD, which in turn outperforms traditional SGD in scenarios with non-isotropic gradients where (non-private) Adagrad provably outperforms SGD. The major…
University of Minnesota - Twin Cities（明尼苏达大学双城分校）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper studies a class of adaptive gradient based momentum algorithms that update the search directions and learning rates simultaneously using past gradients. This class, which we refer to as the "Adam-type", includes the popular algorithms such as the Adam, AMSGrad and AdaGrad. Despite their popularity in training deep neural networks, the convergence of these algorithms for solving nonconvex problems remains an open question. This paper provides a set of mild sufficient conditions that guarantee the convergence for the Adam-type methods. We prove that under our derived conditions, these…
University of California, Berkeley（加利福尼亚大学伯克利分校）；Toyota Technological Institute at Chicago（芝加哥丰田理工学院）
Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We show that for simple overparameterized problems, adaptive methods often find drastically different solutions than gradient descent (GD) or stochastic gradient descent (SGD). We construct an illustrative binary classification problem where the data is linearly separable, GD and SGD achieve zero test error, and AdaGrad, Adam, and RMSProp attain test errors arbitr…
While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings under which SGD performs poorly in comparison to adaptive methods are not well understood yet. In this paper, we provide empirical and theoretical evidence that a heavy-tailed distribution of the noise in stochastic gradients is one cause of SGD's poor performance. We provide the first tight upper and lower convergence bounds for adaptive gradient methods under …
The success of deep learning can be attributed to various factors such as increase in computational power, large datasets, deep convolutional neural networks, optimizers etc. Particularly, the choice of optimizer affects the generalization, convergence rate, and training stability. Stochastic Gradient Descent (SGD) is a first order iterative optimizer that updates the gradient uniformly for all parameters. This uniform update may not be suitable across the entire training phase. A rudimentary solution for this is to employ a fine-tuned learning rate scheduler which decreases learning rate as a…
Facebook AI Research（Facebook人工智能研究院）；Princeton University（普林斯顿大学）
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 image-to-image tasks in vision, and recurrent and bidirectionally-masked models in natural language processing. For each of these tasks, MADGRAD matches or outperforms both SGD and ADAM in test set performance, even on problems for which adaptive methods normally perform poorly.
Massachusetts Institute of Technology（麻省理工学院）；University of California, San Diego（加利福尼亚大学圣迭戈分校）
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 (e.g. Adagrad, Adam, etc.) have become prominent methods of choice for machine learning practitioners. While a large number of works have demonstrated that these first order optimization methods can achieve sub-linear or linear convergence, we establish local quadratic convergence for stochastic gradient descent with adaptive step size for problems such as matri…
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 o…
How do simple rotations affect the implicit bias of Adam?
Committee on Computational and Applied Mathematics, University of Chicago（计算与应用数学委员会，芝加哥大学）；Department of Electrical & Computer Engineering, University of Washington（电气与计算机工程系，华盛顿大学）；NSF-Simons National Institute for Theory and Mathematics in Biology（NSF-西蒙斯国家理论与生物数学研究所）；Department of Statistics, Department of Computer Science, and Data Science Institute, University of Chicago（统计系、计算机科学系和数据科学研究所，芝加哥大学）
Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks
ELLIS Institute Tübingen（图宾根埃利斯研究所）；MPI-IS Tübingen（图宾根马克斯·普朗克研究所）；AI Center, Germany（德国人工智能中心）；CCM, Flatiron Institute, Simons Foundation（CCM，Flatiron研究所，Simons基金会）；New York, US（美国纽约）
Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness
Robert Bosch Center for Cyber Physical Systems, IISc Bengaluru（罗伯特博世网络物理系统中心，印度科学研究所班加罗尔）；Undergraduate Program, IISc Bengaluru（印度科学研究所班加罗尔本科项目）；Department of Computational Data Sciences, IISc Bengaluru（印度科学研究所班加罗尔计算数据科学系）；Department of Computer Science and Automation, IISc Bengaluru（印度科学研究所班加罗尔计算机科学与自动化系）；Tata Consultancy Services Research, Mumbai（塔塔咨询服务研究院，孟买）；System and Control Engineering, IIT Bombay（印度理工学院孟买分校系统与控制工程系）；Centre for Infrastructure, Sustainable Transportation and Urban Planning, IISc Bengaluru（印度科学研究所班加罗尔基础设施、可持续交通与城市规划中心）
University of Padua（帕多瓦大学）；Università di Bologna（博洛尼亚大学）
Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on a minibatch. Several variants of SGD have been proposed to make adaptive step sizes for each parameter (adaptive gradient) and take into account the previous updates (momentum). Among several alternative of SGD the most popular are AdaGrad, AdaDelta, RMSProp and Adam which scale coordinates of the gradient by square roots of some form of averaging of the sq…
Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks
The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））；Vietnam Academy of Science and Technology（越南科学技术研究院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
In this work, we propose an optimization algorithm which we call norm-adapted gradient descent. This algorithm is similar to other gradient-based optimization algorithms like Adam or Adagrad in that it adapts the learning rate of stochastic gradient descent at each iteration. However, rather than using statistical properties of observed gradients, norm-adapted gradient descent relies on a first-order estimate of the effect of a standard gradient descent update step, much like the Newton-Raphson method in many dimensions. Our algorithm can also be compared to quasi-Newton methods, but we seek r…
University of Toronto（多伦多大学）；Vector Institute（矢量研究所）
The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate schemes, such as AdaGrad and Adam, and (2) accelerated schemes, such as heavy-ball and Nesterov momentum. In this paper, we propose a new optimization algorithm, Lookahead, that is orthogonal to these previous approaches and iteratively updates two sets of weights. Intuitively, the algorithm chooses a search direction by looking ahead at the sequence of fast weig…
A model for multi-attack classification to improve intrusion detection performance using deep learning approaches
University College of Engineering(A), Osmania University（奥斯马尼亚大学（A）工程学院）；Vasavi College of Engineering（瓦萨维工程学院）；Bhavans Vivekananda College（巴万斯维韦卡南达学院）；KG Reddy College of Engineering & Technology（KG雷迪工程与技术学院）
Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based on higher order curvature information such as Fisher Scoring have been proposed to precondition the noise in order to achieve better convergence. In this paper, we describe an adaptive method to estimate the parameters of the noise and conduct experiments on well-known model architectures to show that the adaptively preconditioned SGLD method achieves converg…
Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation
School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Vietnam Academy of Science and Technology（越南科学技术研究院）；Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）深圳大数据研究院）
Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
Department of Computer Science, Purdue University, West Lafayette, USA（计算机科学系，普渡大学，西拉法叶，美国）；Edwardson School of Industrial Engineering, Purdue University, West Lafayette, USA（工业工程学院，普渡大学，西拉法叶，美国）
Many popular first-order optimization methods (e.g., Momentum, AdaGrad, Adam) accelerate the convergence rate of deep learning models. However, these algorithms require auxiliary parameters, which cost additional memory proportional to the number of parameters in the model. The problem is becoming more severe as deep learning models continue to grow larger in order to learn from complex, large-scale datasets. Our proposed solution is to maintain a linear sketch to compress the auxiliary variables. We demonstrate that our technique has the same performance as the full-sized baseline, while usin…
Shizuoka University（静冈大学）；Shonan Institute of Technology（湘南工科大学）
Recent studies incorporate Nesterov's accelerated gradient method for the acceleration of gradient based training. The Nesterov's Accelerated Quasi-Newton (NAQ) method has shown to drastically improve the convergence speed compared to the conventional quasi-Newton method. This paper implements NAQ for non-convex optimization on Tensorflow. Two modifications have been proposed to the original NAQ algorithm to ensure global convergence and eliminate linesearch. The performance of the proposed algorithm - mNAQ is evaluated on standard non-convex function approximation benchmark problems and micro…
Forecasting of time series in continuous systems becomes an increasingly relevant task due to recent developments in IoT and 5G. The popular forecasting model ARIMA is applied to a large variety of applications for decades. An online variant of ARIMA applies the Online Newton Step in order to learn the underlying process of the time series. This optimization method has pitfalls concerning the computational complexity and convergence. Thus, this work focuses on the computational less expensive Online Gradient Descent optimization method, which became popular for learning of neural networks in r…
DiDi AI Labs（滴滴人工智能实验室）；Peking University（北京大学）；Zhejiang University（浙江大学）；University of Southern California（南加州大学）；Beijing Institute of Big Data Research（北京大数据研究院）
Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGrad to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of Adam and AMSG…
Why is Normalization Preferred? A Worst-Case Complexity Theory for Stochastically Preconditioned SGD under Heavy-Tailed Noise
Department of Mathematics, University of California, Berkeley, CA, USA（加州大学伯克利分校数学系）；Department of EECS, University of California, Berkeley, CA, USA（加州大学伯克利分校电子工程与计算机科学系）；Department of IEOR, University of California, Berkeley, CA, USA（加州大学伯克利分校工业工程与运营研究系）
In the context of deep learning, many optimization methods use gradient covariance information in order to accelerate the convergence of Stochastic Gradient Descent. In particular, starting with Adagrad, a seemingly endless line of research advocates the use of diagonal approximations of the so-called empirical Fisher matrix in stochastic gradient-based algorithms, with the most prominent one arguably being Adam. However, in recent years, several works cast doubt on the theoretical basis of preconditioning with the empirical Fisher matrix, and it has been shown that more sophisticated approxim…
