English
Related papers

Related papers: The Optimal Condition Number for ReLU Function

200 papers

The development of effective initialization methods requires an understanding of random neural networks. In this work, a rigorous probabilistic analysis of deep unbiased Leaky ReLU networks is provided. We prove a Law of Large Numbers and a…

Machine Learning · Statistics 2026-02-12 Constantin Kogler , Tassilo Schwarz , Samuel Kittle

Gradient descent (GD) type optimization schemes are the standard instruments to train fully connected feedforward artificial neural networks (ANNs) with rectified linear unit (ReLU) activation and can be considered as temporal…

Optimization and Control · Mathematics 2022-02-24 Shokhrukh Ibragimov , Arnulf Jentzen , Timo Kröger , Adrian Riekert

Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its simplicity, it suffers from gradient sparsity and dead-neuron…

Machine Learning · Computer Science 2025-12-03 Ashkan Shakarami , Yousef Yeganeh , Azade Farshad , Lorenzo Nicolè , Stefano Ghidoni , Nassir Navab

We study the type of solutions to which stochastic gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. Our results are based on a dynamical stability analysis. In the…

Machine Learning · Computer Science 2023-07-03 Mor Shpigel Nacson , Rotem Mulayoff , Greg Ongie , Tomer Michaeli , Daniel Soudry

We provide a convergence analysis of gradient descent for the problem of agnostically learning a single ReLU function with moderate bias under Gaussian distributions. Unlike prior work that studies the setting of zero bias, we consider the…

Machine Learning · Computer Science 2024-11-05 Pranjal Awasthi , Alex Tang , Aravindan Vijayaraghavan

Neuron death is a complex phenomenon with implications for model trainability: the deeper the network, the lower the probability of finding a valid initialization. In this work, we derive both upper and lower bounds on the probability that…

Machine Learning · Computer Science 2021-06-14 Blaine Rister , Daniel L. Rubin

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

The Rectified Linear Unit (ReLU) is a foundational activation function in artficial neural networks. Recent literature frequently misattributes its origin to the 2018 (initial) version of this paper, which exclusively investigated ReLU at…

Neural and Evolutionary Computing · Computer Science 2026-04-15 Abien Fred Agarap

Batch Normalization (BN) is a commonly used technique to accelerate and stabilize training of deep neural networks. Despite its empirical success, a full theoretical understanding of BN is yet to be developed. In this work, we analyze BN…

Machine Learning · Computer Science 2022-03-22 Tolga Ergen , Arda Sahiner , Batu Ozturkler , John Pauly , Morteza Mardani , Mert Pilanci

We provide a theoretical explanation of the role of the number of nodes at each layer in deep neural networks. We prove that the largest variation of a deep neural network with ReLU activation function arises when the layer with the fewest…

Machine Learning · Statistics 2018-12-11 Yongdai Kim , Dongha Kim

Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Pravendra Singh , Munender Varshney , Vinay P. Namboodiri

In this paper, we study the trainability of rectified linear unit (ReLU) networks. A ReLU neuron is said to be dead if it only outputs a constant for any input. Two death states of neurons are introduced; tentative and permanent death. A…

Machine Learning · Computer Science 2020-10-23 Yeonjong Shin , George Em Karniadakis

The choice of architecture of a neural network influences which functions will be realizable by that neural network and, as a result, studying the expressiveness of a chosen architecture has received much attention. In ReLU neural networks,…

Machine Learning · Computer Science 2024-12-18 Natalie Brownlowe , Christopher R. Cornwell , Ethan Montes , Gabriel Quijano , Grace Stulman , Na Zhang

The training process of neural networks usually optimize weights and bias parameters of linear transformations, while nonlinear activation functions are pre-specified and fixed. This work develops a systematic approach to constructing…

Machine Learning · Computer Science 2024-10-29 Zhengqi Liu , Shuhao Cao , Yuwen Li , Ludmil Zikatanov

We establish a functional large deviation principle for fully connected multi-layer perceptrons with i.i.d. Gaussian weights (LeCun initialization) and general Lipschitz activation functions, including therefore the popular case of ReLU.…

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise,…

Machine Learning · Computer Science 2023-04-07 Ilja Kuzborskij , Csaba Szepesvári

Rectified-linear-unit (ReLU) neural networks, which play a prominent role in deep learning, generate continuous and piecewise-linear (CPWL) functions. While they provide a powerful parametric representation, the mapping between the…

Numerical Analysis · Mathematics 2022-03-11 Alexis Goujon , Joaquim Campos , Michael Unser

Whereas recovery of the manifold from data is a well-studied topic, approximation rates for functions defined on manifolds are less known. In this work, we study a regression problem with inputs on a $d^*$-dimensional manifold that is…

Machine Learning · Statistics 2019-08-05 Johannes Schmidt-Hieber

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

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