English
Related papers

Related papers: Decoupling Gating from Linearity

200 papers

We present a greedy-based approach to construct an efficient single hidden layer neural network with the ReLU activation that approximates a target function. In our approach we obtain a shallow network by utilizing a greedy algorithm with…

Machine Learning · Computer Science 2021-10-01 Anton Dereventsov , Armenak Petrosyan , Clayton Webster

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Recently there has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that, for a large class of piecewise smooth functions, the number of neurons needed by a shallow network to…

Machine Learning · Computer Science 2017-03-07 Shiyu Liang , R. Srikant

Many empirical studies have demonstrated the performance benefits of conditional computation in neural networks, including reduced inference time and power consumption. We study the fundamental limits of neural conditional computation from…

Machine Learning · Computer Science 2023-03-21 Erdem Koyuncu

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an extent, the character of blocking negative values may suppress…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Xuanyi Dong , Guoliang Kang , Kun Zhan , Yi Yang

Solving mixed-integer optimization problems with embedded neural networks with ReLU activation functions is challenging. Big-M coefficients that arise in relaxing binary decisions related to these functions grow exponentially with the…

Optimization and Control · Mathematics 2025-02-06 Christoph Plate , Mirko Hahn , Alexander Klimek , Caroline Ganzer , Kai Sundmacher , Sebastian Sager

Recent papers on the theory of representation learning has shown the importance of a quantity called diversity when generalizing from a set of source tasks to a target task. Most of these papers assume that the function mapping shared…

Machine Learning · Statistics 2021-06-01 Ziping Xu , Ambuj Tewari

We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Instead of using backpropagation to learn features, GLNs have a distributed and local credit assignment…

Machine Learning · Computer Science 2020-10-22 David Budden , Adam Marblestone , Eren Sezener , Tor Lattimore , Greg Wayne , Joel Veness

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions…

Machine Learning · Computer Science 2022-09-07 Qingguo Hong , Jonathan W. Siegel , Qinyang Tan , Jinchao Xu

We develop fast algorithms and robust software for convex optimization of two-layer neural networks with ReLU activation functions. Our work leverages a convex reformulation of the standard weight-decay penalized training problem as a set…

Machine Learning · Computer Science 2025-04-10 Aaron Mishkin , Arda Sahiner , Mert Pilanci

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden…

Machine Learning · Computer Science 2020-08-18 Mert Pilanci , Tolga Ergen

Recent results in nonparametric regression show that deep learning, i.e., neural network estimates with many hidden layers, are able to circumvent the so-called curse of dimensionality in case that suitable restrictions on the structure of…

Machine Learning · Statistics 2020-09-30 Michael Kohler , Sophie Langer

Rectified Linear Units (ReLU) are the default choice for activation functions in deep neural networks. While they demonstrate excellent empirical performance, ReLU activations can fall victim to the dead neuron problem. In these cases, the…

Machine Learning · Computer Science 2023-02-14 Tim Whitaker , Darrell Whitley

Recently, path norm was proposed as a new capacity measure for neural networks with Rectified Linear Unit (ReLU) activation function, which takes the rescaling-invariant property of ReLU into account. It has been shown that the…

Machine Learning · Computer Science 2019-08-22 Shuxin Zheng , Qi Meng , Huishuai Zhang , Wei Chen , Nenghai Yu , Tie-Yan Liu

Understanding generalization in overparameterized neural networks hinges on the interplay between the data geometry, neural architecture, and training dynamics. In this paper, we theoretically explore how data geometry controls this…

Machine Learning · Statistics 2026-05-08 Tongtong Liang , Alexander Cloninger , Rahul Parhi , Yu-Xiang Wang

We present a complimentary objective for training recurrent neural networks (RNN) with gating units that helps with regularization and interpretability of the trained model. Attention-based RNN models have shown success in many difficult…

Machine Learning · Computer Science 2015-06-30 Jonathan Raiman , Szymon Sidor

A ReLU neural network leads to a finite polyhedral decomposition of input space and a corresponding finite dual graph. We show that while this dual graph is a coarse quantization of input space, it is sufficiently robust that it can be…

Algebraic Topology · Mathematics 2023-07-03 Yajing Liu , Christina M Cole , Chris Peterson , Michael Kirby

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently…

Neural and Evolutionary Computing · Computer Science 2014-12-12 Junyoung Chung , Caglar Gulcehre , KyungHyun Cho , Yoshua Bengio

Convolutional neural networks have been successful in solving many socially important and economically significant problems. This ability to learn complex high-dimensional functions hierarchically can be attributed to the use of nonlinear…

Machine Learning · Computer Science 2025-04-15 Mathew Mithra Noel , Arunkumar L , Advait Trivedi , Praneet Dutta

We develop a corrective mechanism for neural network approximation: the total available non-linear units are divided into multiple groups and the first group approximates the function under consideration, the second group approximates the…

Machine Learning · Computer Science 2020-06-23 Guy Bresler , Dheeraj Nagaraj