English
Related papers

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

200 papers

This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism;…

We explore convergence of deep neural networks with the popular ReLU activation function, as the depth of the networks tends to infinity. To this end, we introduce the notion of activation domains and activation matrices of a ReLU network.…

Machine Learning · Computer Science 2023-01-11 Yuesheng Xu , Haizhang Zhang

We consider the injectivity property of the ReLU networks layers. Determining the ReLU injectivity capacity (ratio of the number of layer's inputs and outputs) is established as isomorphic to determining the capacity of the so-called…

Machine Learning · Statistics 2024-10-29 Mihailo Stojnic

This paper studies a problem of learning surface mesh via implicit functions in an emerging field of deep learning surface reconstruction, where implicit functions are popularly implemented as multi-layer perceptrons (MLPs) with rectified…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Jiabao Lei , Kui Jia

We show that taking the width and depth to infinity in a deep neural network with skip connections, when branches are scaled by $1/\sqrt{depth}$ (the only nontrivial scaling), result in the same covariance structure no matter how that limit…

Machine Learning · Statistics 2023-08-11 Soufiane Hayou , Greg Yang

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representations. In these…

Machine Learning · Computer Science 2021-02-24 Etai Littwin , Tomer Galanti , Lior Wolf , Greg Yang

Can a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD globally optimizes this learning problem for a two-layer…

Machine Learning · Computer Science 2021-07-29 Roei Sarussi , Alon Brutzkus , Amir Globerson

LayerNorm is a critical component in modern large language models (LLMs) for stabilizing training and ensuring smooth optimization. However, it introduces significant challenges in mechanistic interpretability, outlier feature suppression,…

Machine Learning · Computer Science 2024-11-19 Nandan Kumar Jha , Brandon Reagen

The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…

Machine Learning · Computer Science 2022-04-27 Thien Le , Stefanie Jegelka

Amongst others, the adoption of Rectified Linear Units (ReLUs) is regarded as one of the ingredients of the success of deep learning. ReLU activation has been shown to mitigate the vanishing gradient issue, to encourage sparsity in the…

Machine Learning · Statistics 2021-10-14 Nicola Picchiotti , Marco Gori

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

Implicit deep learning has recently become popular in the machine learning community since these implicit models can achieve competitive performance with state-of-the-art deep networks while using significantly less memory and computational…

Machine Learning · Computer Science 2022-05-17 Tianxiang Gao , Hongyang Gao

This article derives and validates three principles for initialization and architecture selection in finite width graph neural networks (GNNs) with ReLU activations. First, we theoretically derive what is essentially the unique…

Machine Learning · Statistics 2023-06-21 Gage DeZoort , Boris Hanin

Attention mechanisms lie at the heart of modern large language models (LLMs). Straightforward algorithms for forward and backward (gradient) computation take quadratic time, and a line of work initiated by [Alman and Song NeurIPS 2023] and…

Machine Learning · Computer Science 2025-05-23 Josh Alman , Zhao Song

In this paper, we study the generalization ability of the wide residual network on $\mathbb{S}^{d-1}$ with the ReLU activation function. We first show that as the width $m\rightarrow\infty$, the residual network kernel (RNK) uniformly…

Machine Learning · Statistics 2023-05-31 Jianfa Lai , Zixiong Yu , Songtao Tian , Qian Lin

Previous work has demonstrated that attention mechanisms are Turing complete. More recently, it has been shown that a looped 9-layer Transformer can function as a universal programmable computer. In contrast, the multi-layer perceptrons…

Machine Learning · Computer Science 2025-02-21 Yingyu Liang , Zhizhou Sha , Zhenmei Shi , Zhao Song , Yufa Zhou

Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent multimodal safety gap. We study this gap from a…

Artificial Intelligence · Computer Science 2026-05-19 Jiahe Guo , Xiangran Guo , Jiaxuan Chen , Weixiang Zhao , Yanyan Zhao , Yutai Hou , Qianchao Wang , Dandan Tu , Bing Qin

The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propagation (LRP) is a well-established method that transparently…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Seitaro Otsuki , Tsumugi Iida , Félix Doublet , Tsubasa Hirakawa , Takayoshi Yamashita , Hironobu Fujiyoshi , Komei Sugiura

The transformer architecture has driven many successes in a variety of tasks within the field of deep learning, in particular the recent advances in natural language processing (NLP) culminating with large language models (LLM). Adding to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Abdullah Nazhat Abdullah , Tarkan Aydin

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which…

Computer Vision and Pattern Recognition · Computer Science 2016-07-26 Kaiming He , Xiangyu Zhang , Shaoqing Ren , Jian Sun