English
Related papers

Related papers: Precise gradient descent training dynamics for fin…

200 papers

Gradient descent yields zero training loss in polynomial time for deep neural networks despite non-convex nature of the objective function. The behavior of network in the infinite width limit trained by gradient descent can be described by…

Machine Learning · Computer Science 2023-05-29 Yuqing Li , Tao Luo , Nung Kwan Yip

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

This work examines the deep disconnect between existing theoretical analyses of gradient-based algorithms and the practice of training deep neural networks. Specifically, we provide numerical evidence that in large-scale neural network…

Machine Learning · Computer Science 2022-06-20 Jingzhao Zhang , Haochuan Li , Suvrit Sra , Ali Jadbabaie

We develop a mean field theory for batch normalization in fully-connected feedforward neural networks. In so doing, we provide a precise characterization of signal propagation and gradient backpropagation in wide batch-normalized networks…

Neural and Evolutionary Computing · Computer Science 2019-03-07 Greg Yang , Jeffrey Pennington , Vinay Rao , Jascha Sohl-Dickstein , Samuel S. Schoenholz

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence…

Machine Learning · Statistics 2026-03-06 Eloy Mosig , Andrea Agazzi , Dario Trevisan

Much attention has been devoted recently to the generalization puzzle in deep learning: large, deep networks can generalize well, but existing theories bounding generalization error are exceedingly loose, and thus cannot explain this…

Machine Learning · Statistics 2019-01-08 Andrew K. Lampinen , Surya Ganguli

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

This manuscript investigates the one-pass stochastic gradient descent (SGD) dynamics of a two-layer neural network trained on Gaussian data and labels generated by a similar, though not necessarily identical, target function. We rigorously…

Machine Learning · Statistics 2023-02-14 Luca Arnaboldi , Ludovic Stephan , Florent Krzakala , Bruno Loureiro

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

Machine Learning · Computer Science 2024-10-08 Arthur Jacot , Peter Súkeník , Zihan Wang , Marco Mondelli

We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain…

Machine Learning · Computer Science 2024-06-18 Stefano Favaro , Boris Hanin , Domenico Marinucci , Ivan Nourdin , Giovanni Peccati

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

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

A recent goal in the theory of deep learning is to identify how neural networks can escape the "lazy training," or Neural Tangent Kernel (NTK) regime, where the network is coupled with its first order Taylor expansion at initialization.…

Machine Learning · Computer Science 2022-11-29 Eshaan Nichani , Yu Bai , Jason D. Lee

Small generalization errors of over-parameterized neural networks (NNs) can be partially explained by the frequency biasing phenomenon, where gradient-based algorithms minimize the low-frequency misfit before reducing the high-frequency…

Machine Learning · Computer Science 2022-09-27 Annan Yu , Yunan Yang , Alex Townsend

We present a unified convergence theory for gradient-based training of neural network methods for partial differential equations (PDEs), covering both physics-informed neural networks (PINNs) and the Deep Ritz method. For linear PDEs, we…

Numerical Analysis · Mathematics 2025-10-09 Wei Zhao , Tao Luo

The key to generalization is controlling the complexity of the network. However, there is no obvious control of complexity -- such as an explicit regularization term -- in the training of deep networks for classification. We will show that…

Machine Learning · Computer Science 2020-04-14 Andrzej Banburski , Qianli Liao , Brando Miranda , Lorenzo Rosasco , Fernanda De La Torre , Jack Hidary , Tomaso Poggio

We establish the asymptotic implicit bias of gradient descent (GD) for generic non-homogeneous deep networks under exponential loss. Specifically, we characterize three key properties of GD iterates starting from a sufficiently small…

Machine Learning · Computer Science 2025-07-17 Yuhang Cai , Kangjie Zhou , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al.,…

Machine Learning · Statistics 2024-09-06 Hugo Cui , Luca Pesce , Yatin Dandi , Florent Krzakala , Yue M. Lu , Lenka Zdeborová , Bruno Loureiro

The generalization mystery of overparametrized deep nets has motivated efforts to understand how gradient descent (GD) converges to low-loss solutions that generalize well. Real-life neural networks are initialized from small random values…

Machine Learning · Computer Science 2021-11-10 Kaifeng Lyu , Zhiyuan Li , Runzhe Wang , Sanjeev Arora

Performing gradient descent in a wide neural network is equivalent to computing the posterior mean of a Gaussian Process with the Neural Tangent Kernel (NTK-GP), for a specific prior mean and with zero observation noise. However, existing…