English
Related papers

Related papers: How Does Gradient Descent Learn Features -- A Loca…

200 papers

We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance…

Machine Learning · Computer Science 2019-05-29 Preetum Nakkiran , Gal Kaplun , Dimitris Kalimeris , Tristan Yang , Benjamin L. Edelman , Fred Zhang , Boaz Barak

Graph Neural Networks (GNNs) are powerful tools for addressing learning problems on graph structures, with a wide range of applications in molecular biology and social networks. However, the theoretical foundations underlying their…

Machine Learning · Computer Science 2025-01-27 Dhiraj Patel , Anton Savostianov , Michael T. Schaub

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global…

Machine Learning · Statistics 2020-04-28 Colin Wei , Jason D. Lee , Qiang Liu , Tengyu Ma

Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from many random initial points. One thread of work has focused on…

Machine Learning · Computer Science 2020-03-24 Charles G. Frye , James Simon , Neha S. Wadia , Andrew Ligeralde , Michael R. DeWeese , Kristofer E. Bouchard

Many neural network architectures are known to be Turing Complete, and can thus, in principle implement arbitrary algorithms. However, Transformers are unique in that they can implement gradient-based learning algorithms under simple…

Machine Learning · Computer Science 2024-06-05 Xiang Cheng , Yuxin Chen , Suvrit Sra

The performance of a deep neural network is highly dependent on its training, and finding better local optimal solutions is the goal of many optimization algorithms. However, existing optimization algorithms show a preference for descent…

Computer Vision and Pattern Recognition · Computer Science 2019-12-06 Huangxing Lin , Weihong Zeng , Xinghao Ding , Yue Huang , Chenxi Huang , John Paisley

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

Machine Learning · Computer Science 2021-06-14 Quynh Nguyen

A rising trend in theoretical deep learning is to understand why deep learning works through Neural Tangent Kernel (NTK) [jgh18], a kernel method that is equivalent to using gradient descent to train a multi-layer infinitely-wide neural…

Machine Learning · Computer Science 2023-09-15 Lianke Qin , Zhao Song , Baocheng Sun

Despite recent theoretical progress on the non-convex optimization of two-layer neural networks, it is still an open question whether gradient descent on neural networks without unnatural modifications can achieve better sample complexity…

Machine Learning · Computer Science 2023-10-10 Arvind Mahankali , Jeff Z. Haochen , Kefan Dong , Margalit Glasgow , Tengyu Ma

Understanding how deep neural networks learn representations remains a central challenge in machine learning theory. In this work, we propose a feature-centric framework for analyzing neural network training by relating weight updates to…

Machine Learning · Computer Science 2026-05-08 Taehun Cha , Daniel Beaglehole , Adityanarayanan Radhakrishnan , Donghun Lee

We propose that the grokking phenomenon, where the train loss of a neural network decreases much earlier than its test loss, can arise due to a neural network transitioning from lazy training dynamics to a rich, feature learning regime. To…

Machine Learning · Statistics 2024-04-12 Tanishq Kumar , Blake Bordelon , Samuel J. Gershman , Cengiz Pehlevan

We study the natural gradient method for learning in deep Bayesian networks, including neural networks. There are two natural geometries associated with such learning systems consisting of visible and hidden units. One geometry is related…

Machine Learning · Computer Science 2020-05-22 Nihat Ay

Gradients have been used to quantify feature importance in machine learning models. Unfortunately, in nonlinear deep networks, not only individual neurons but also the whole network can saturate, and as a result an important input feature…

Machine Learning · Computer Science 2016-11-16 Mukund Sundararajan , Ankur Taly , Qiqi Yan

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

Federated Learning (FL) is an emerging learning scheme that allows different distributed clients to train deep neural networks together without data sharing. Neural networks have become popular due to their unprecedented success. To the…

Machine Learning · Computer Science 2021-05-12 Baihe Huang , Xiaoxiao Li , Zhao Song , Xin Yang

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

Despite the extreme popularity of deep learning in science and industry, its formal understanding is limited. This thesis puts forth notions of rank as key for developing a theory of deep learning, focusing on the fundamental aspects of…

Machine Learning · Computer Science 2024-12-31 Noam Razin

Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an…

Machine Learning · Statistics 2019-05-09 Arild Nøkland , Lars Hiller Eidnes

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad…

We study the hardness of learning unitary transformations in $U(d)$ via gradient descent on time parameters of alternating operator sequences. We provide numerical evidence that, despite the non-convex nature of the loss landscape, gradient…

Quantum Physics · Physics 2020-02-20 Bobak Toussi Kiani , Seth Lloyd , Reevu Maity
‹ Prev 1 3 4 5 6 7 10 Next ›