English
Related papers

Related papers: Can an MLP Absorb Its Own Skip Connection?

200 papers

We provide the first proof of learning rate transfer with width in a linear multi-layer perceptron (MLP) parametrized with $\mu$P, a neural network parameterization designed to ``maximize'' feature learning in the infinite-width limit. We…

Machine Learning · Statistics 2026-02-26 Soufiane Hayou

Federated graph learning (FGL) has recently emerged as a promising privacy-preserving paradigm that enables distributed graph learning across multiple data owners. A critical privacy concern in federated learning is whether an adversary can…

Machine Learning · Computer Science 2026-01-28 Shuyue Wei , Wantong Chen , Tongyu Wei , Chen Gong , Yongxin Tong , Lizhen Cui

We investigate the implications of removing bias in ReLU networks regarding their expressivity and learning dynamics. We first show that two-layer bias-free ReLU networks have limited expressivity: the only odd function two-layer bias-free…

Machine Learning · Computer Science 2025-04-29 Yedi Zhang , Andrew Saxe , Peter E. Latham

An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification…

Machine Learning · Computer Science 2019-01-21 Thomas Villmann , John Ravichandran , Andrea Villmann , David Nebel , Marika Kaden

We study the loss surface of neural networks equipped with a hinge loss criterion and ReLU or leaky ReLU nonlinearities. Any such network defines a piecewise multilinear form in parameter space. By appealing to harmonic analysis we show…

Machine Learning · Computer Science 2018-07-24 Thomas Laurent , James von Brecht

We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning…

Machine Learning · Computer Science 2020-11-13 Elisa Oostwal , Michiel Straat , Michael Biehl

The implicit bias towards solutions with favorable properties is believed to be a key reason why neural networks trained by gradient-based optimization can generalize well. While the implicit bias of gradient flow has been widely studied…

Machine Learning · Computer Science 2023-10-31 Yiwen Kou , Zixiang Chen , Quanquan Gu

Understanding the role of (stochastic) gradient descent (SGD) in the training and generalisation of deep neural networks (DNNs) with ReLU activation has been the object study in the recent past. In this paper, we make use of deep gated…

Machine Learning · Computer Science 2020-03-03 Chandrashekar Lakshminarayanan , Amit Vikram Singh

Previous work has questioned the conditions under which the decision regions of a neural network are connected and further showed the implications of the corresponding theory to the problem of adversarial manipulation of classifiers. It has…

Machine Learning · Computer Science 2019-01-28 Trung Le , Dinh Phung

In this paper we study the problem of learning Rectified Linear Units (ReLUs) which are functions of the form $max(0,<w,x>)$ with $w$ denoting the weight vector. We study this problem in the high-dimensional regime where the number of…

Machine Learning · Computer Science 2017-08-03 Mahdi Soltanolkotabi

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model…

Computation and Language · Computer Science 2024-04-05 Hongfei Xu , Yang Song , Qiuhui Liu , Josef van Genabith , Deyi Xiong

We analyse the convergence of one-hidden-layer ReLU networks trained by gradient flow on $n$ data points. Our main contribution leverages the high dimensionality of the ambient space, which implies low correlation of the input samples, to…

Machine Learning · Statistics 2025-12-02 Léo Dana , Francis Bach , Loucas Pillaud-Vivien

A wide variety of activation functions have been proposed for neural networks. The Rectified Linear Unit (ReLU) is especially popular today. There are many practical reasons that motivate the use of the ReLU. This paper provides new…

Machine Learning · Statistics 2020-10-19 Rahul Parhi , Robert D. Nowak

We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture. Using techniques from mixed-integer optimization, polyhedral theory, and tropical…

Machine Learning · Computer Science 2024-07-18 Christoph Hertrich , Amitabh Basu , Marco Di Summa , Martin Skutella

Flip graphs of combinatorial and geometric objects are at the heart of many deep structural insights and connections between different branches of discrete mathematics and computer science. They also provide a natural framework for the…

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 present a simple proof for the benefit of depth in multi-layer feedforward network with rectified activation ("depth separation"). Specifically we present a sequence of classification problems indexed by $m$ such that (a) for any fixed…

Machine Learning · Computer Science 2021-01-19 Asaf Amrami , Yoav Goldberg

We investigate to what extent it is possible to solve linear inverse problems with $ReLu$ networks. Due to the scaling invariance arising from the linearity, an optimal reconstruction function $f$ for such a problem is positive homogeneous,…

Machine Learning · Computer Science 2023-08-08 Stefan Bamberger , Reinhard Heckel , Felix Krahmer

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise…

Machine Learning · Computer Science 2023-10-03 Dmitry Chistikov , Matthias Englert , Ranko Lazic