English
Related papers

Related papers: Which Neural Net Architectures Give Rise To Explod…

200 papers

A key challenge in modern deep learning theory is to explain the remarkable success of gradient-based optimization methods when training large-scale, complex deep neural networks. Though linear convergence of such methods has been proved…

Machine Learning · Computer Science 2025-09-30 Yash Jakhmola

We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model…

Machine Learning · Statistics 2018-07-16 Smitha Milli , Ludwig Schmidt , Anca D. Dragan , Moritz Hardt

Gradient networks can be used to model the dominant structure of complex networks. Previous works have focused on random gradient networks. Here we study gradient networks that minimize jamming on substrate networks with scale-free and…

Statistical Mechanics · Physics 2009-11-13 Natali Gulbahce

Deep residual architectures, such as ResNet and the Transformer, have enabled models of unprecedented depth, yet a formal understanding of why depth is so effective remains an open question. A popular intuition, following Veit et al.…

Machine Learning · Computer Science 2025-10-09 Benoit Dherin , Michael Munn

Graph neural networks have become a staple in problems addressing learning and analysis of data defined over graphs. However, several results suggest an inherent difficulty in extracting better performance by increasing the number of…

Machine Learning · Computer Science 2021-03-30 Diego Valsesia , Giulia Fracastoro , Enrico Magli

We propose a novel approach to addressing the vanishing (or exploding) gradient problem in deep neural networks. We construct a new architecture for deep neural networks where all layers (except the output layer) of the network are a…

Machine Learning · Computer Science 2021-04-27 Gordon MacDonald , Andrew Godbout , Bryn Gillcash , Stephanie Cairns

Neural networks are complex functions of both their inputs and parameters. Much prior work in deep learning theory analyzes the distribution of network outputs at a fixed a set of inputs (e.g. a training dataset) over random initializations…

Disordered Systems and Neural Networks · Physics 2025-04-08 Mike Winer , Boris Hanin

A substantial body of empirical work documents the lack of robustness in deep learning models to adversarial examples. Recent theoretical work proved that adversarial examples are ubiquitous in two-layers networks with sub-exponential width…

Machine Learning · Computer Science 2023-01-24 Andrea Montanari , Yuchen Wu

The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding…

Machine Learning · Computer Science 2024-08-23 Taeyoung Kim , Hongseok Yang

For a long time, designing neural architectures that exhibit high performance was considered a dark art that required expert hand-tuning. One of the few well-known guidelines for architecture design is the avoidance of exploding gradients,…

Machine Learning · Computer Science 2021-06-10 George Philipp , Jaime G. Carbonell

We characterize the computational power of neural networks that follow the graph neural network (GNN) architecture, not restricted to aggregate-combine GNNs or other particular types. We establish an exact correspondence between the…

Machine Learning · Computer Science 2024-11-22 Timon Barlag , Vivian Holzapfel , Laura Strieker , Jonni Virtema , Heribert Vollmer

Benign overfitting refers to how over-parameterized neural networks can fit training data perfectly and generalize well to unseen data. While this has been widely investigated theoretically, existing works are limited to two-layer networks…

Machine Learning · Computer Science 2024-10-28 Shuning Shang , Xuran Meng , Yuan Cao , Difan Zou

We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given…

Machine Learning · Computer Science 2018-10-12 Gauri Jagatap , Chinmay Hegde

Neural Tangent Kernel (NTK) theory is widely used to study the dynamics of infinitely-wide deep neural networks (DNNs) under gradient descent. But do the results for infinitely-wide networks give us hints about the behavior of real…

Machine Learning · Computer Science 2022-02-02 Mariia Seleznova , Gitta Kutyniok

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

Motivated by the flexibility of biological neural networks whose connectivity structure changes significantly during their lifetime, we introduce the Unstructured Recursive Network (URN) and demonstrate that it can exhibit similar…

Machine Learning · Computer Science 2019-11-27 Siavash Golkar

The training process of ReLU neural networks often exhibits complicated nonlinear phenomena. The nonlinearity of models and non-convexity of loss pose significant challenges for theoretical analysis. Therefore, most previous theoretical…

Machine Learning · Computer Science 2023-12-29 Mingze Wang , Chao Ma

We study mechanisms to characterize how the asymptotic convergence of backpropagation in deep architectures, in general, is related to the network structure, and how it may be influenced by other design choices including activation type,…

Machine Learning · Computer Science 2017-03-02 Vamsi K Ithapu , Sathya N Ravi , Vikas Singh

This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is general, and the (optimal) Bayes risk is not necessarily…

Machine Learning · Computer Science 2021-11-05 Ziwei Ji , Justin D. Li , Matus Telgarsky

In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classical notions of function complexity, which typically favor…

Machine Learning · Statistics 2018-06-20 Roman Novak , Yasaman Bahri , Daniel A. Abolafia , Jeffrey Pennington , Jascha Sohl-Dickstein
‹ Prev 1 4 5 6 7 8 10 Next ›