English
Related papers

Related papers: When does gradient descent with logistic loss inte…

200 papers

We provide a detailed asymptotic study of gradient flow trajectories and their implicit optimization bias when minimizing the exponential loss over "diagonal linear networks". This is the simplest model displaying a transition between…

Machine Learning · Computer Science 2020-07-15 Edward Moroshko , Suriya Gunasekar , Blake Woodworth , Jason D. Lee , Nathan Srebro , Daniel Soudry

We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network architecture. These…

Machine Learning · Computer Science 2021-06-18 Alejandro Cabana , Luis F. Lago-Fernández

We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under some conditions, the parameter values obtained using GD achieve…

Machine Learning · Computer Science 2021-05-17 Siddhartha Satpathi , R Srikant

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

We show that gradient descent on full-width linear convolutional networks of depth $L$ converges to a linear predictor related to the $\ell_{2/L}$ bridge penalty in the frequency domain. This is in contrast to linearly fully connected…

Machine Learning · Computer Science 2019-01-14 Suriya Gunasekar , Jason Lee , Daniel Soudry , Nathan Srebro

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer $l$, the number…

Machine Learning · Computer Science 2020-06-30 Yuandong Tian

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of…

Machine Learning · Computer Science 2026-03-02 Sacchit Kale , Piyushi Manupriya , Pierre Marion , Francis Bach , Anant Raj

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 paper shows that the implicit bias of gradient descent on linearly separable data is exactly characterized by the optimal solution of a dual optimization problem given by a smoothed margin, even for general losses. This is in contrast…

Machine Learning · Computer Science 2020-11-13 Ziwei Ji , Matus Telgarsky

Gradient descent (GD) type optimization methods are the standard instrument to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Despite the great success of GD type optimization methods in numerical…

Optimization and Control · Mathematics 2022-12-29 Arnulf Jentzen , Adrian Riekert

Gradient descent is a simple and widely used optimization method for machine learning. For homogeneous linear classifiers applied to separable data, gradient descent has been shown to converge to the maximal margin (or equivalently, the…

Machine Learning · Statistics 2019-07-30 Denali Molitor , Deanna Needell , Rachel Ward

Existing analyses of optimization in deep learning are either continuous, focusing on (variants of) gradient flow, or discrete, directly treating (variants of) gradient descent. Gradient flow is amenable to theoretical analysis, but is…

Machine Learning · Computer Science 2021-12-30 Omer Elkabetz , Nadav Cohen

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a…

Machine Learning · Computer Science 2023-02-10 Karl Hajjar , Lenaic Chizat

The gradient descent (GD) method -- is a fundamental and likely the most popular optimization algorithm in machine learning (ML), with a history traced back to a paper in 1847 (Cauchy, 1847). It was studied under various assumptions,…

Optimization and Control · Mathematics 2025-02-20 Aleksandr Lobanov , Alexander Gasnikov , Eduard Gorbunov , Martin Takáč

In this paper, we study the optimality gap between two-layer ReLU networks regularized with weight decay and their convex relaxations. We show that when the training data is random, the relative optimality gap between the original problem…

Machine Learning · Computer Science 2024-07-15 Sungyoon Kim , Mert Pilanci

The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how…

Machine Learning · Computer Science 2017-12-11 Daniel Jiwoong Im , Michael Tao , Kristin Branson

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

Numerical Analysis · Mathematics 2020-11-02 Austin R. Benson , Anil Damle , Alex Townsend

We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We show that the gradient dynamics of such networks are…

Machine Learning · Computer Science 2019-06-20 Francis Williams , Matthew Trager , Claudio Silva , Daniele Panozzo , Denis Zorin , Joan Bruna

We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary,…

Machine Learning · Statistics 2019-06-19 Yongdai Kim , Ilsang Ohn , Dongha Kim