English
Related papers

Related papers: The Quenching-Activation Behavior of the Gradient …

200 papers

In this work, we study the training and generalization performance of two-layer neural networks (NNs) after one gradient descent step under structured data modeled by Gaussian mixtures. While previous research has extensively analyzed this…

Machine Learning · Statistics 2025-05-20 Samet Demir , Zafer Dogan

Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting global minimum that is attained by a common optimization…

Machine Learning · Statistics 2026-03-06 Kuo-Wei Lai , Guanghui Wang , Molei Tao , Vidya Muthukumar

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

For high-dimensional Gaussian data, we investigate theoretically how the features of a two-layer neural network adapt to the structure of the target function through a few large batch gradient descent steps, leading to an improvement in the…

Machine Learning · Statistics 2025-06-05 Yatin Dandi , Florent Krzakala , Bruno Loureiro , Luca Pesce , Ludovic Stephan

Double-descent curves in neural networks describe the phenomenon that the generalisation error initially descends with increasing parameters, then grows after reaching an optimal number of parameters which is less than the number of data…

Machine Learning · Statistics 2023-05-29 Ouns El Harzli , Bernardo Cuenca Grau , Guillermo Valle-Pérez , Ard A. Louis

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

It has been observed by Belkin et al.\ that over-parametrized neural networks exhibit a `double descent' phenomenon. That is, as the model complexity (as reflected in the number of features) increases, the test error initially decreases,…

Optimization and Control · Mathematics 2025-09-16 Vivek Shripad Borkar

There has been a recent surge of interest in understanding the convergence of gradient descent (GD) and stochastic gradient descent (SGD) in overparameterized neural networks. Most previous works assume that the training data is provided a…

Machine Learning · Statistics 2021-05-04 Jiaming Xu , Hanjing Zhu

Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization error initially…

Machine Learning · Computer Science 2021-08-30 Cory Stephenson , Tyler Lee

Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and least understood quality of SGD is that it generalizes…

Machine Learning · Computer Science 2020-07-03 Erhan Bilal

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for…

Machine Learning · Computer Science 2023-05-29 Zefan Li , Bingbing Ni , Teng Li , WenJun Zhang , Wen Gao

This work analyzes the solution trajectory of gradient-based algorithms via a novel basis function decomposition. We show that, although solution trajectories of gradient-based algorithms may vary depending on the learning task, they behave…

Machine Learning · Computer Science 2022-10-05 Jianhao Ma , Lingjun Guo , Salar Fattahi

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

Machine Learning · Computer Science 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

Gradient Descent (GD) and its variants are the primary tool for enabling efficient training of recurrent dynamical systems such as Recurrent Neural Networks (RNNs), Neural ODEs and Gated Recurrent units (GRUs). The dynamics that are formed…

Machine Learning · Computer Science 2025-07-10 James Hazelden , Laura Driscoll , Eli Shlizerman , Eric Shea-Brown

The mini-batch stochastic gradient descent (SGD) algorithm is widely used in training machine learning models, in particular deep learning models. We study SGD dynamics under linear regression and two-layer linear networks, with an easy…

Optimization and Control · Mathematics 2020-04-29 Xin Qian , Diego Klabjan

Natural gradient descent is a principled method for adapting the parameters of a statistical model on-line using an underlying Riemannian parameter space to redefine the direction of steepest descent. The algorithm is examined via methods…

Disordered Systems and Neural Networks · Physics 2009-10-31 Magnus Rattray , David Saad

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion