English
Related papers

Related papers: Why gradient clipping accelerates training: A theo…

200 papers

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws…

Machine Learning · Computer Science 2018-06-08 Fuxun Yu , Zirui Xu , Yanzhi Wang , Chenchen Liu , Xiang Chen

We present a family of algorithms, called descent algorithms, for optimizing convex and non-convex functions. We also introduce a new first-order algorithm, called rescaled gradient descent (RGD), and show that RGD achieves a faster…

Optimization and Control · Mathematics 2020-01-07 Ashia Wilson , Lester Mackey , Andre Wibisono

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Many neural networks deployed in the real world scenarios are trained using cross entropy based loss functions. From the optimization perspective, it is known that the behavior of first order methods such as gradient descent crucially…

Machine Learning · Computer Science 2023-10-09 Zhu Wang , Praveen Raj Veluswami , Harsh Mishra , Sathya N. Ravi

How sensitive should machine learning models be to input changes? We tackle the question of model smoothness and show that it is a useful inductive bias which aids generalization, adversarial robustness, generative modeling and…

Machine Learning · Statistics 2021-07-08 Mihaela Rosca , Theophane Weber , Arthur Gretton , Shakir Mohamed

In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block…

Machine Learning · Computer Science 2018-04-24 Adams Wei Yu , Lei Huang , Qihang Lin , Ruslan Salakhutdinov , Jaime Carbonell

Deep unfolding is a promising deep-learning technique, whose network architecture is based on expanding the recursive structure of existing iterative algorithms. Although convergence acceleration is a remarkable advantage of deep unfolding,…

Machine Learning · Computer Science 2020-10-27 Satoshi Takabe , Tadashi Wadayama

Sign-based stochastic methods have gained attention due to their ability to achieve robust performance despite using only the sign information for parameter updates. However, the current convergence analysis of sign-based methods relies on…

Machine Learning · Computer Science 2023-10-24 Tao Sun , Congliang Chen , Peng Qiao , Li Shen , Xinwang Liu , Dongsheng Li

Recent advances in convex optimization have leveraged computer-assisted proofs to develop optimized first-order methods that improve over classical algorithms. However, each optimized method is specially tailored for a particular problem…

Optimization and Control · Mathematics 2025-07-01 Jinho Bok , Jason M. Altschuler

For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the original image. However, Santurkar et al. (2019) demonstrated…

Machine Learning · Computer Science 2019-10-24 Simran Kaur , Jeremy Cohen , Zachary C. Lipton

In gradient descent dynamics of neural networks, the top eigenvalue of the loss Hessian (sharpness) displays a variety of robust phenomena throughout training. This includes early time regimes where the sharpness may decrease during early…

Machine Learning · Computer Science 2025-02-17 Dayal Singh Kalra , Tianyu He , Maissam Barkeshli

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is…

Machine Learning · Computer Science 2023-12-29 Daphna Weinshall , Gad Cohen , Dan Amir

The usual approach to developing and analyzing first-order methods for smooth convex optimization assumes that the gradient of the objective function is uniformly smooth with some Lipschitz constant $L$. However, in many settings the…

Optimization and Control · Mathematics 2017-10-11 Haihao Lu , Robert M. Freund , Yurii Nesterov

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant.…

Machine Learning · Computer Science 2021-11-03 Yujia Huang , Huan Zhang , Yuanyuan Shi , J Zico Kolter , Anima Anandkumar

Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they…

Machine Learning · Computer Science 2024-07-03 Mohamed Elsayed , Qingfeng Lan , Clare Lyle , A. Rupam Mahmood

We consider non-convex stochastic optimization using first-order algorithms for which the gradient estimates may have heavy tails. We show that a combination of gradient clipping, momentum, and normalized gradient descent yields convergence…

Machine Learning · Computer Science 2021-11-10 Ashok Cutkosky , Harsh Mehta

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

The integration of contextual embeddings into the optimization processes of large language models is an advancement in natural language processing. The Context-Aware Neural Gradient Mapping framework introduces a dynamic gradient adjustment…

Computation and Language · Computer Science 2025-04-25 David Boldo , Lily Pemberton , Gabriel Thistledown , Jacob Fairchild , Felix Kowalski

When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more…

Machine Learning · Computer Science 2019-12-21 Ruoyu Sun

Normalized gradient descent has shown substantial success in speeding up the convergence of exponentially-tailed loss functions (which includes exponential and logistic losses) on linear classifiers with separable data. In this paper, we go…

Machine Learning · Computer Science 2023-06-28 Hossein Taheri , Christos Thrampoulidis
‹ Prev 1 8 9 10 Next ›