English
Related papers

Related papers: Student Specialization in Deep ReLU Networks With …

200 papers

Training very deep neural networks is still an extremely challenging task. The common solution is to use shortcut connections and normalization layers, which are both crucial ingredients in the popular ResNet architecture. However, there is…

Machine Learning · Computer Science 2022-03-16 Guodong Zhang , Aleksandar Botev , James Martens

We revisit the problem of learning a single neuron with ReLU activation under Gaussian input with square loss. We particularly focus on the over-parameterization setting where the student network has $n\ge 2$ neurons. We prove the global…

Machine Learning · Computer Science 2023-10-11 Weihang Xu , Simon S. Du

We study the necessary and sufficient complexity of ReLU neural networks---in terms of depth and number of weights---which is required for approximating classifier functions in $L^2$. As a model class, we consider the set $\mathcal{E}^\beta…

Functional Analysis · Mathematics 2018-05-23 Philipp Petersen , Felix Voigtlaender

The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. Two types of GNNs are investigated, depending on whether labels are attached…

Machine Learning · Computer Science 2020-12-08 Qunwei Li , Shaofeng Zou , Wenliang Zhong

Differentially private learning is essential for training models on sensitive data, but empirical studies consistently show that it can degrade performance, introduce fairness issues like disparate impact, and reduce adversarial robustness.…

Machine Learning · Computer Science 2026-04-21 Ruichen Xu , Kexin Chen

In this article we study fully-connected feedforward deep ReLU ANNs with an arbitrarily large number of hidden layers and we prove convergence of the risk of the GD optimization method with random initializations in the training of such…

Optimization and Control · Mathematics 2022-07-14 Arnulf Jentzen , Adrian Riekert

Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse (NC) phenomenon, where simple feature structures emerge at…

Machine Learning · Computer Science 2025-10-27 Hancheng Min , Zhihui Zhu , René Vidal

In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one hidden layer to *global optimality* with runtime…

Machine Learning · Computer Science 2018-03-01 Raman Arora , Amitabh Basu , Poorya Mianjy , Anirbit Mukherjee

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain linear transformations…

Machine Learning · Computer Science 2020-03-03 Difan Zou , Philip M. Long , Quanquan Gu

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small initialisations are generally associated to a feature…

Machine Learning · Computer Science 2025-09-16 Etienne Boursier , Nicolas Flammarion

We consider the phenomenon of adversarial examples in ReLU networks with independent gaussian parameters. For networks of constant depth and with a large range of widths (for instance, it suffices if the width of each layer is polynomial in…

Machine Learning · Computer Science 2021-06-25 Peter L. Bartlett , Sébastien Bubeck , Yeshwanth Cherapanamjeri

We consider supervised learning with $n$ labels and show that layerwise SGD on residual networks can efficiently learn a class of hierarchical models. This model class assumes the existence of an (unknown) label hierarchy $L_1 \subseteq L_2…

Machine Learning · Computer Science 2026-01-05 Amit Daniely

Consider the following fundamental learning problem: given input examples $x \in \mathbb{R}^d$ and their vector-valued labels, as defined by an underlying generative neural network, recover the weight matrices of this network. We consider…

Data Structures and Algorithms · Computer Science 2018-11-06 Ainesh Bakshi , Rajesh Jayaram , David P. Woodruff

Previous work has demonstrated that MLPs within ReLU Transformers exhibit high levels of sparsity, with many of their activations equal to zero for any given token. We build on that work to more deeply explore how token-level sparsity…

Machine Learning · Computer Science 2024-07-11 Cody Wild , Jesper Anderson

Fine-tuning is a common practice in deep learning, achieving excellent generalization results on downstream tasks using relatively little training data. Although widely used in practice, it is lacking strong theoretical understanding. We…

Machine Learning · Computer Science 2021-11-09 Gal Shachaf , Alon Brutzkus , Amir Globerson

Training a one-node neural network with ReLU activation function (One-Node-ReLU) is a fundamental optimization problem in deep learning. In this paper, we begin with proving the NP-hardness of training One-Node-ReLU. We then present an…

Optimization and Control · Mathematics 2019-05-23 Santanu S. Dey , Guanyi Wang , Yao Xie

The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice…

Computer Vision and Pattern Recognition · Computer Science 2023-01-24 Souvik Kundu , Shunlin Lu , Yuke Zhang , Jacqueline Liu , Peter A. Beerel

In studying the expressiveness of neural networks, an important question is whether there are functions which can only be approximated by sufficiently deep networks, assuming their size is bounded. However, for constant depths, existing…

Machine Learning · Computer Science 2020-12-29 Gal Vardi , Ohad Shamir

We study the implicit bias towards low-rank weight matrices when training neural networks (NN) with Weight Decay (WD). We prove that when a ReLU NN is sufficiently trained with Stochastic Gradient Descent (SGD) and WD, its weight matrix is…

Machine Learning · Computer Science 2024-10-04 Ke Chen , Chugang Yi , Haizhao Yang

We consider a one-hidden-layer leaky ReLU network of arbitrary width trained by stochastic gradient descent (SGD) following an arbitrary initialization. We prove that SGD produces neural networks that have classification accuracy…

Machine Learning · Computer Science 2021-02-16 Spencer Frei , Yuan Cao , Quanquan Gu
‹ Prev 1 4 5 6 7 8 10 Next ›